Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4759 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.6886. Min Act: -0.1700
Data Index: 2160076 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.5011. Min Act: -0.1700
Data Index: 8338729 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.5323. Min Act: -0.1700
Data Index: 2160077 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.5011. Min Act: -0.1700
Data Index: 4879087 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.4698. Min Act: -0.1700
Data Index: 1406596 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.5011. Min Act: -0.1700
Data Index: 1462872 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.4698. Min Act: -0.1700
Data Index: 6595518 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.4698. Min Act: -0.1700
Data Index: 1594738 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3761. Min Act: -0.1700
Data Index: 8338719 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3448. Min Act: -0.1700
Data Index: 4337896 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3448. Min Act: -0.1700
Data Index: 1395092 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3448. Min Act: -0.1700
Data Index: 4879086 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3136. Min Act: -0.1700
Data Index: 5906381 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3448. Min Act: -0.1700
Data Index: 5367591 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3448. Min Act: -0.1700
Data Index: 4972801 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3136. Min Act: -0.1700
Data Index: 396965 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3136. Min Act: -0.1700
Data Index: 8338718 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.3136. Min Act: -0.1700
Data Index: 605457 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.2511. Min Act: -0.1700
Data Index: 7084968 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6886. Min Range: -6.6886
Max Act: 6.2823. Min Act: -0.1700
Data Index: 6281276 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19