Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.1317. Min Act: -0.1700
Data Index: 8268745 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.1004. Min Act: -0.1700
Data Index: 4352827 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.1004. Min Act: -0.1700
Data Index: 1918109 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.0692. Min Act: -0.1700
Data Index: 8009709 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.0067. Min Act: -0.1700
Data Index: 3349029 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.0067. Min Act: -0.1700
Data Index: 5317396 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9754. Min Act: -0.1700
Data Index: 5780058 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9754. Min Act: -0.1700
Data Index: 1037207 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1317. Min Range: -5.1317
Max Act: 5.0067. Min Act: -0.1700
Data Index: 2158984 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9442. Min Act: -0.1700
Data Index: 668402 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9129. Min Act: -0.1700
Data Index: 5316862 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9129. Min Act: -0.1700
Data Index: 2586943 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4638130 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8817. Min Act: -0.1700
Data Index: 2096572 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.9129. Min Act: -0.1700
Data Index: 414954 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8817. Min Act: -0.1700
Data Index: 8173106 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8817. Min Act: -0.1700
Data Index: 4242666 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8504. Min Act: -0.1700
Data Index: 255182 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8504. Min Act: -0.1699
Data Index: 2480177 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1317. Min Range: -5.1317
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2708192 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19