Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.7177. Min Act: -0.1700
Data Index: 5530336 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.5927. Min Act: -0.1700
Data Index: 2227295 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.5302. Min Act: -0.1700
Data Index: 122808 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4989. Min Act: -0.1700
Data Index: 759573 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4677. Min Act: -0.1700
Data Index: 2413326 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4677. Min Act: -0.1700
Data Index: 88612 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4677. Min Act: -0.1700
Data Index: 8660203 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4677. Min Act: -0.1700
Data Index: 2591220 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4364. Min Act: -0.1700
Data Index: 258716 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4364. Min Act: -0.1700
Data Index: 1784791 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.4052. Min Act: -0.1700
Data Index: 4294822 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3739. Min Act: -0.1700
Data Index: 3778448 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3739. Min Act: -0.1700
Data Index: 2434493 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3427. Min Act: -0.1700
Data Index: 6699184 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3739. Min Act: -0.1700
Data Index: 6254597 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3739. Min Act: -0.1700
Data Index: 5723059 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3427. Min Act: -0.1700
Data Index: 7140501 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3427. Min Act: -0.1700
Data Index: 1691796 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3114. Min Act: -0.1700
Data Index: 1121128 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7177. Min Range: -4.7177
Max Act: 4.3427. Min Act: -0.1700
Data Index: 597221 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19