Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0283. Min Range: -4.0283
Max Act: 4.0283. Min Act: -0.1700
Data Index: 7052308 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.9814. Min Act: -0.1700
Data Index: 1814151 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.9501. Min Act: -0.1700
Data Index: 808316 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.9345. Min Act: -0.1700
Data Index: 7772831 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.9032. Min Act: -0.1700
Data Index: 3961078 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.8720. Min Act: -0.1700
Data Index: 2689122 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.8720. Min Act: -0.1700
Data Index: 5700240 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.8250. Min Act: -0.1700
Data Index: 1575188 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7781. Min Act: -0.1700
Data Index: 4286194 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7938. Min Act: -0.1700
Data Index: 3372390 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7625. Min Act: -0.1700
Data Index: 1055949 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7781. Min Act: -0.1700
Data Index: 8230241 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7625. Min Act: -0.1700
Data Index: 2765684 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7469. Min Act: -0.1700
Data Index: 6863682 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7469. Min Act: -0.1700
Data Index: 5219193 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7312. Min Act: -0.1700
Data Index: 4070685 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7469. Min Act: -0.1700
Data Index: 1634643 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7156. Min Act: -0.1700
Data Index: 6753091 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7156. Min Act: -0.1700
Data Index: 74761 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0283. Min Range: -4.0283
Max Act: 3.7156. Min Act: -0.1700
Data Index: 5731442 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19