Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4684 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.8380. Min Act: -0.1700
Data Index: 7914629 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6818. Min Act: -0.1700
Data Index: 8136 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6818. Min Act: -0.1700
Data Index: 2174231 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6818. Min Act: -0.1700
Data Index: 4957717 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6193. Min Act: -0.1700
Data Index: 1402360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6193. Min Act: -0.1700
Data Index: 4434474 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6193. Min Act: -0.1700
Data Index: 6183999 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.6193. Min Act: -0.1700
Data Index: 1192405 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.5568. Min Act: -0.1700
Data Index: 152206 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.5880. Min Act: -0.1700
Data Index: 4843480 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.5568. Min Act: -0.1700
Data Index: 4909962 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.5255. Min Act: -0.1700
Data Index: 4923744 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4943. Min Act: -0.1700
Data Index: 950066 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4943. Min Act: -0.1700
Data Index: 2143999 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4943. Min Act: -0.1700
Data Index: 8618172 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4630. Min Act: -0.1700
Data Index: 8255262 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4943. Min Act: -0.1700
Data Index: 5335933 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4943. Min Act: -0.1700
Data Index: 3143344 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4318. Min Act: -0.1700
Data Index: 5211655 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8380. Min Range: -6.8380
Max Act: 6.4318. Min Act: -0.1700
Data Index: 5291746 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19