Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.3567. Min Act: -0.1700
Data Index: 2384280 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.2942. Min Act: -0.1700
Data Index: 3935473 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.1067. Min Act: -0.1700
Data Index: 4660947 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.1067. Min Act: -0.1700
Data Index: 7595294 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.1067. Min Act: -0.1700
Data Index: 5168895 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.0442. Min Act: -0.1700
Data Index: 1669228 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3567. Min Range: -8.3567
Max Act: 8.0442. Min Act: -0.1700
Data Index: 3010024 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.9192. Min Act: -0.1700
Data Index: 8237490 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.7630. Min Act: -0.1700
Data Index: 4123811 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.7317. Min Act: -0.1700
Data Index: 5612619 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.6692. Min Act: -0.1700
Data Index: 4387176 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.6692. Min Act: -0.1700
Data Index: 3624330 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.6692. Min Act: -0.1700
Data Index: 5636898 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.6380. Min Act: -0.1700
Data Index: 8595846 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.6380. Min Act: -0.1700
Data Index: 6685629 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.5442. Min Act: -0.1700
Data Index: 1361095 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.5442. Min Act: -0.1700
Data Index: 4272898 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.5130. Min Act: -0.1700
Data Index: 6438302 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.5130. Min Act: -0.1700
Data Index: 97151 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3567. Min Range: -8.3567
Max Act: 7.4817. Min Act: -0.1700
Data Index: 4539094 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19