Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.6166. Min Act: -0.1700
Data Index: 3638898 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.3666. Min Act: -0.1700
Data Index: 4813775 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.2416. Min Act: -0.1700
Data Index: 2973971 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.1791. Min Act: -0.1700
Data Index: 5390409 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.0541. Min Act: -0.1700
Data Index: 7607510 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.1166. Min Act: -0.1700
Data Index: 3482413 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6166. Min Range: -9.6166
Max Act: 9.1791. Min Act: -0.1700
Data Index: 1852991 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.9916. Min Act: -0.1700
Data Index: 2647492 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.9916. Min Act: -0.1700
Data Index: 6902225 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.9291. Min Act: -0.1700
Data Index: 40971 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.9291. Min Act: -0.1700
Data Index: 6177577 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8666. Min Act: -0.1700
Data Index: 7340081 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8666. Min Act: -0.1700
Data Index: 7662235 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8666. Min Act: -0.1700
Data Index: 5390411 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8041. Min Act: -0.1700
Data Index: 5940487 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8041. Min Act: -0.1700
Data Index: 3435306 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.8041. Min Act: -0.1700
Data Index: 6209846 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.7416. Min Act: -0.1700
Data Index: 6576006 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.7416. Min Act: -0.1700
Data Index: 6773240 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6166. Min Range: -9.6166
Max Act: 8.6791. Min Act: -0.1700
Data Index: 6846950 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19