Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.9487. Min Act: -0.1700
Data Index: 5791742 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.8237. Min Act: -0.1700
Data Index: 5214675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.7925. Min Act: -0.1700
Data Index: 986446 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.6050. Min Act: -0.1700
Data Index: 8094315 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.5737. Min Act: -0.1700
Data Index: 242749 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.5425. Min Act: -0.1700
Data Index: 3876935 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.5737. Min Act: -0.1700
Data Index: 1945912 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.5112. Min Act: -0.1700
Data Index: 4532088 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.5112. Min Act: -0.1700
Data Index: 2358022 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4800. Min Act: -0.1700
Data Index: 5037900 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 7458292 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4800. Min Act: -0.1700
Data Index: 1272973 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4800. Min Act: -0.1700
Data Index: 7028103 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 1529961 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 3832225 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 655552 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 3901169 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4470303 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4175. Min Act: -0.1700
Data Index: 5008675 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9487. Min Range: -5.9487
Max Act: 5.4175. Min Act: -0.1700
Data Index: 1685507 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19