Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.8073. Min Act: -0.1700
Data Index: 4991263 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7595. Min Act: -0.1700
Data Index: 6220248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7595. Min Act: -0.1700
Data Index: 2056153 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7595. Min Act: -0.1700
Data Index: 6004411 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7435. Min Act: -0.1700
Data Index: 8280341 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7276. Min Act: -0.1700
Data Index: 2037762 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6796. Min Act: -0.1700
Data Index: 4118750 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.7116. Min Act: -0.1700
Data Index: 8568963 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6796. Min Act: -0.1700
Data Index: 6379235 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6956. Min Act: -0.1700
Data Index: 2056150 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6956. Min Act: -0.1700
Data Index: 7675621 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6796. Min Act: -0.1700
Data Index: 393818 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6796. Min Act: -0.1700
Data Index: 6228897 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6475. Min Act: -0.1700
Data Index: 1768281 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6635. Min Act: -0.1700
Data Index: 835686 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6635. Min Act: -0.1700
Data Index: 6879644 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6796. Min Act: -0.1700
Data Index: 6948305 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6475. Min Act: -0.1700
Data Index: 4174775 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6635. Min Act: -0.1700
Data Index: 7320572 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8073. Min Range: -2.8073
Max Act: 2.6475. Min Act: -0.1700
Data Index: 5005171 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19