Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5197 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.9605. Min Act: -0.1700
Data Index: 4102337 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.8980. Min Act: -0.1700
Data Index: 7581182 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.8355. Min Act: -0.1700
Data Index: 4902126 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.8355. Min Act: -0.1700
Data Index: 5429583 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.6480. Min Act: -0.1700
Data Index: 907855 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.7105. Min Act: -0.1700
Data Index: 2917305 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.6480. Min Act: -0.1700
Data Index: 1290782 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.6480. Min Act: -0.1700
Data Index: 2237256 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.6480. Min Act: -0.1700
Data Index: 2917304 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.5855. Min Act: -0.1700
Data Index: 2258394 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.5855. Min Act: -0.1700
Data Index: 1971310 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.5230. Min Act: -0.1700
Data Index: 233962 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.4605. Min Act: -0.1700
Data Index: 4045463 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.4605. Min Act: -0.1700
Data Index: 7074607 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.4605. Min Act: -0.1700
Data Index: 6921326 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.3980. Min Act: -0.1700
Data Index: 3795901 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.3980. Min Act: -0.1700
Data Index: 4208460 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.3980. Min Act: -0.1700
Data Index: 2473562 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.3980. Min Act: -0.1700
Data Index: 3544471 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9605. Min Range: -9.9605
Max Act: 9.3980. Min Act: -0.1700
Data Index: 1971308 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19