Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0279. Min Range: -6.0279
Max Act: 6.0279. Min Act: -0.1700
Data Index: 6357568 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.9029. Min Act: -0.1700
Data Index: 5421404 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.9029. Min Act: -0.1700
Data Index: 182506 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8717. Min Act: -0.1700
Data Index: 2193206 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8717. Min Act: -0.1700
Data Index: 7464100 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8717. Min Act: -0.1700
Data Index: 7948702 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8717. Min Act: -0.1700
Data Index: 6977583 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8404. Min Act: -0.1700
Data Index: 7684323 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.8092. Min Act: -0.1700
Data Index: 2538438 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.7467. Min Act: -0.1700
Data Index: 2291984 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.7467. Min Act: -0.1700
Data Index: 5953652 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.7154. Min Act: -0.1700
Data Index: 1786992 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4999824 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.7154. Min Act: -0.1700
Data Index: 6196691 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6842. Min Act: -0.1700
Data Index: 8796528 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6842. Min Act: -0.1700
Data Index: 5115665 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6217. Min Act: -0.1700
Data Index: 4946487 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6529. Min Act: -0.1700
Data Index: 8268496 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6217. Min Act: -0.1700
Data Index: 6920994 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0279. Min Range: -6.0279
Max Act: 5.6217. Min Act: -0.1700
Data Index: 6611427 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19