Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6111 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1908. Min Range: -7.1908
Max Act: 7.1908. Min Act: -0.1700
Data Index: 1002724 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1908. Min Range: -7.1908
Max Act: 7.0658. Min Act: -0.1700
Data Index: 3168387 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1908. Min Range: -7.1908
Max Act: 7.0033. Min Act: -0.1700
Data Index: 3605182 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.8470. Min Act: -0.1700
Data Index: 8085531 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.9095. Min Act: -0.1700
Data Index: 4458496 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.8470. Min Act: -0.1700
Data Index: 5188666 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.8158. Min Act: -0.1700
Data Index: 6003981 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.7533. Min Act: -0.1700
Data Index: 6187130 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.7220. Min Act: -0.1700
Data Index: 573058 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 8184931 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 5602682 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 4463632 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 831339 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6595. Min Act: -0.1700
Data Index: 4930122 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.6283. Min Act: -0.1700
Data Index: 6114252 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.5970. Min Act: -0.1700
Data Index: 6922196 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 7679423 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.5970. Min Act: -0.1700
Data Index: 1050759 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.5345. Min Act: -0.1700
Data Index: 4676620 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1908. Min Range: -7.1908
Max Act: 6.5345. Min Act: -0.1700
Data Index: 2443712 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19