Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2580. Min Range: -6.2580
Max Act: 6.2580. Min Act: -0.1700
Data Index: 7054996 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7580. Min Act: -0.1700
Data Index: 7746319 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7268. Min Act: -0.1700
Data Index: 3070212 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.6643. Min Act: -0.1700
Data Index: 8338840 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.6643. Min Act: -0.1700
Data Index: 4233031 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.5705. Min Act: -0.1700
Data Index: 7437572 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.5080. Min Act: -0.1700
Data Index: 7960499 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.4143. Min Act: -0.1700
Data Index: 2678032 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.4143. Min Act: -0.1700
Data Index: 8156347 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3830. Min Act: -0.1700
Data Index: 3974466 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3830. Min Act: -0.1700
Data Index: 8111232 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3830. Min Act: -0.1700
Data Index: 1573526 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3830. Min Act: -0.1700
Data Index: 56420 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3518. Min Act: -0.1700
Data Index: 516531 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3830. Min Act: -0.1700
Data Index: 7775087 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3518. Min Act: -0.1700
Data Index: 637037 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3518. Min Act: -0.1700
Data Index: 2598377 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3518. Min Act: -0.1700
Data Index: 2021680 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3205. Min Act: -0.1700
Data Index: 1375489 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.3205. Min Act: -0.1700
Data Index: 2923972 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19