Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7761. Min Act: -0.1700
Data Index: 1536970 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7761. Min Act: -0.1700
Data Index: 4602005 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7448. Min Act: -0.1700
Data Index: 3289913 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7448. Min Act: -0.1700
Data Index: 804944 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7448. Min Act: -0.1700
Data Index: 235322 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7136. Min Act: -0.1700
Data Index: 2781300 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6823. Min Act: -0.1700
Data Index: 7752999 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6198. Min Act: -0.1700
Data Index: 5884029 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5261. Min Act: -0.1700
Data Index: 235325 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4636. Min Act: -0.1700
Data Index: 2781320 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4636. Min Act: -0.1700
Data Index: 5631317 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7587411 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7249992 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 2781333 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 2781322 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 7775642 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.3698. Min Act: -0.1700
Data Index: 2996016 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.3698. Min Act: -0.1700
Data Index: 2781307 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.3698. Min Act: -0.1700
Data Index: 5323942 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.3698. Min Act: -0.1700
Data Index: 2031440 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19