Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0109. Min Range: -6.0109
Max Act: 6.0109. Min Act: -0.1700
Data Index: 1075325 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.9172. Min Act: -0.1700
Data Index: 7529022 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.8547. Min Act: -0.1700
Data Index: 2431955 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.8234. Min Act: -0.1700
Data Index: 869394 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.8234. Min Act: -0.1700
Data Index: 8213373 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.7609. Min Act: -0.1700
Data Index: 1189297 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6984. Min Act: -0.1700
Data Index: 3096747 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.7297. Min Act: -0.1700
Data Index: 8302079 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6672. Min Act: -0.1700
Data Index: 6811078 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6984. Min Act: -0.1700
Data Index: 1599119 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6984. Min Act: -0.1700
Data Index: 1671036 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6672. Min Act: -0.1700
Data Index: 6119236 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6672. Min Act: -0.1700
Data Index: 1180279 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6672. Min Act: -0.1700
Data Index: 2139302 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6359. Min Act: -0.1700
Data Index: 1565190 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6359. Min Act: -0.1700
Data Index: 8674404 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6672. Min Act: -0.1700
Data Index: 7632764 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6359. Min Act: -0.1700
Data Index: 7379347 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6047. Min Act: -0.1700
Data Index: 2809943 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0109. Min Range: -6.0109
Max Act: 5.6047. Min Act: -0.1700
Data Index: 885294 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19