Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4382. Min Range: -5.4382
Max Act: 5.4382. Min Act: -0.1700
Data Index: 1544276 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4382. Min Range: -5.4382
Max Act: 5.2507. Min Act: -0.1700
Data Index: 5680773 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4382. Min Range: -5.4382
Max Act: 5.2195. Min Act: -0.1700
Data Index: 4925213 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4382. Min Range: -5.4382
Max Act: 5.1882. Min Act: -0.1700
Data Index: 7602141 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.9695. Min Act: -0.1700
Data Index: 6082614 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.9382. Min Act: -0.1700
Data Index: 3493183 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3154372 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3386426 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.9070. Min Act: -0.1700
Data Index: 5680774 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.8757. Min Act: -0.1700
Data Index: 1901116 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4989522 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4585403 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7820. Min Act: -0.1700
Data Index: 2873829 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 1009354 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 8563106 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7820. Min Act: -0.1700
Data Index: 995182 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6883465 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6929487 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7820. Min Act: -0.1700
Data Index: 5256979 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4382. Min Range: -5.4382
Max Act: 4.7507. Min Act: -0.1700
Data Index: 5775035 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19