Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.9735. Min Act: -0.1700
Data Index: 3970205 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.7860. Min Act: -0.1700
Data Index: 7691476 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.7860. Min Act: -0.1700
Data Index: 1617627 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.5360. Min Act: -0.1700
Data Index: 249551 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.5360. Min Act: -0.1700
Data Index: 7637426 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.5360. Min Act: -0.1700
Data Index: 3091182 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.4735. Min Act: -0.1700
Data Index: 7696778 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.4735. Min Act: -0.1700
Data Index: 7759235 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.3485. Min Act: -0.1700
Data Index: 4719924 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.4110. Min Act: -0.1700
Data Index: 5377786 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.3485. Min Act: -0.1700
Data Index: 1652696 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2860. Min Act: -0.1700
Data Index: 7228369 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.3485. Min Act: -0.1700
Data Index: 7760201 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2860. Min Act: -0.1700
Data Index: 1878882 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2860. Min Act: -0.1700
Data Index: 5239030 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2860. Min Act: -0.1700
Data Index: 4953081 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2235. Min Act: -0.1700
Data Index: 219090 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2235. Min Act: -0.1700
Data Index: 5994053 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2235. Min Act: -0.1700
Data Index: 3002756 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9735. Min Range: -10.9735
Max Act: 10.2235. Min Act: -0.1700
Data Index: 530199 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19