Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.6369. Min Act: -0.1700
Data Index: 3378113 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.4333. Min Act: -0.1700
Data Index: 1998153 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.4020. Min Act: -0.1700
Data Index: 1488666 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.3078. Min Act: -0.1700
Data Index: 3560461 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2450. Min Act: -0.1700
Data Index: 6421149 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2450. Min Act: -0.1700
Data Index: 4970916 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2450. Min Act: -0.1700
Data Index: 4970902 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2293. Min Act: -0.1700
Data Index: 6421152 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2136. Min Act: -0.1700
Data Index: 3099353 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2293. Min Act: -0.1700
Data Index: 6421161 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1979. Min Act: -0.1700
Data Index: 8765356 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.2136. Min Act: -0.1700
Data Index: 6421160 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1979. Min Act: -0.1700
Data Index: 4420163 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1821. Min Act: -0.1700
Data Index: 6421162 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1664. Min Act: -0.1700
Data Index: 6421148 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1349. Min Act: -0.1700
Data Index: 7019671 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1034. Min Act: -0.1700
Data Index: 8286569 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1192. Min Act: -0.1700
Data Index: 786089 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1349. Min Act: -0.1700
Data Index: 5567402 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6369. Min Range: -3.6369
Max Act: 3.1192. Min Act: -0.1700
Data Index: 2258019 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19