Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.8755. Min Act: -0.1700
Data Index: 3669530 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.5630. Min Act: -0.1700
Data Index: 2231974 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3755. Min Act: -0.1700
Data Index: 798485 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 4784958 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 6647582 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1880. Min Act: -0.1700
Data Index: 2036089 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1880. Min Act: -0.1700
Data Index: 6417250 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1255. Min Act: -0.1700
Data Index: 1376181 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1255. Min Act: -0.1700
Data Index: 2265428 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1255. Min Act: -0.1700
Data Index: 310587 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.0005. Min Act: -0.1700
Data Index: 3349298 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 8125364 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 4371187 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 7808436 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.8443. Min Act: -0.1700
Data Index: 4455493 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.8130. Min Act: -0.1700
Data Index: 8285463 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.7193. Min Act: -0.1700
Data Index: 6984458 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.7193. Min Act: -0.1700
Data Index: 6075908 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.7193. Min Act: -0.1700
Data Index: 5231961 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8755. Min Range: -8.8755
Max Act: 7.7193. Min Act: -0.1700
Data Index: 8158731 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19