Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.3858. Min Act: -0.1700
Data Index: 4286317 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.3233. Min Act: -0.1700
Data Index: 6946284 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.2921. Min Act: -0.1700
Data Index: 3634663 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 1362229 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 5962985 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.2296. Min Act: -0.1700
Data Index: 3954250 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1983. Min Act: -0.1700
Data Index: 6174754 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1358. Min Act: -0.1700
Data Index: 5746305 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1358. Min Act: -0.1700
Data Index: 1542096 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1358. Min Act: -0.1700
Data Index: 2893869 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1358. Min Act: -0.1700
Data Index: 1071904 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1358. Min Act: -0.1700
Data Index: 8193349 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1046. Min Act: -0.1700
Data Index: 8270987 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1046. Min Act: -0.1700
Data Index: 7975397 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1046. Min Act: -0.1700
Data Index: 2026584 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.1046. Min Act: -0.1700
Data Index: 1558075 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.0421. Min Act: -0.1700
Data Index: 1146343 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.0421. Min Act: -0.1700
Data Index: 5317312 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.0421. Min Act: -0.1700
Data Index: 199607 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3858. Min Range: -5.3858
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1793339 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19