Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.7922. Min Act: -0.1700
Data Index: 6961529 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.8234. Min Act: -0.1700
Data Index: 2347273 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.6047. Min Act: -0.1700
Data Index: 1901115 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.5109. Min Act: -0.1700
Data Index: 3563333 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4484. Min Act: -0.1700
Data Index: 1972541 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4484. Min Act: -0.1700
Data Index: 4625503 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4797. Min Act: -0.1700
Data Index: 585431 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4797. Min Act: -0.1700
Data Index: 1399467 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4484. Min Act: -0.1700
Data Index: 367601 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4484. Min Act: -0.1700
Data Index: 5714576 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4484. Min Act: -0.1700
Data Index: 8233221 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4172. Min Act: -0.1700
Data Index: 6083456 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4172. Min Act: -0.1700
Data Index: 329547 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.4172. Min Act: -0.1700
Data Index: 6099424 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3859. Min Act: -0.1700
Data Index: 4524515 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3547. Min Act: -0.1700
Data Index: 2816864 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3859. Min Act: -0.1700
Data Index: 2467836 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3859. Min Act: -0.1700
Data Index: 4107950 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3859. Min Act: -0.1700
Data Index: 2147210 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8234. Min Range: -4.8234
Max Act: 4.3547. Min Act: -0.1700
Data Index: 4255809 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19