Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.5347. Min Act: -0.1700
Data Index: 4220309 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.4097. Min Act: -0.1700
Data Index: 928751 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.3159. Min Act: -0.1699
Data Index: 1306065 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.2847. Min Act: -0.1700
Data Index: 3007742 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.3159. Min Act: -0.1700
Data Index: 3550051 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.2534. Min Act: -0.1700
Data Index: 930261 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.2222. Min Act: -0.1700
Data Index: 28168 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.2222. Min Act: -0.1700
Data Index: 2970360 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.1909. Min Act: -0.1700
Data Index: 3666842 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.2222. Min Act: -0.1700
Data Index: 5047927 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.1284. Min Act: -0.1700
Data Index: 561516 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.1284. Min Act: -0.1700
Data Index: 7879030 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.1597. Min Act: -0.1700
Data Index: 3133256 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0972. Min Act: -0.1700
Data Index: 6167954 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0972. Min Act: -0.1700
Data Index: 105367 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0659. Min Act: -0.1700
Data Index: 7393543 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0659. Min Act: -0.1700
Data Index: 8261040 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0347. Min Act: -0.1700
Data Index: 5086535 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0347. Min Act: -0.1700
Data Index: 7685280 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5347. Min Range: -8.5347
Max Act: 8.0347. Min Act: -0.1700
Data Index: 5591834 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19