Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4988 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.8109. Min Act: -0.1700
Data Index: 6948464 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.7796. Min Act: -0.1700
Data Index: 277291 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6484816 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 3475206 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6903497 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8017625 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6593362 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 2467222 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4295256 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 3560017 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6367247 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6537458 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5609. Min Act: -0.1700
Data Index: 3712326 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5296. Min Act: -0.1700
Data Index: 265378 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5609. Min Act: -0.1700
Data Index: 1474396 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5609. Min Act: -0.1700
Data Index: 4938520 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5296. Min Act: -0.1700
Data Index: 2596728 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5296. Min Act: -0.1700
Data Index: 6601962 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5296. Min Act: -0.1700
Data Index: 390691 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8109. Min Range: -5.8109
Max Act: 5.5296. Min Act: -0.1700
Data Index: 5067146 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19