Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.8195. Min Act: -0.1700
Data Index: 1821782 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.6945. Min Act: -0.1700
Data Index: 2983408 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.6945. Min Act: -0.1700
Data Index: 6777847 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.4445. Min Act: -0.1700
Data Index: 807509 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.3820. Min Act: -0.1700
Data Index: 2172325 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.3820. Min Act: -0.1700
Data Index: 5655724 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.2570. Min Act: -0.1700
Data Index: 4705582 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.3195. Min Act: -0.1700
Data Index: 6596455 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.2570. Min Act: -0.1700
Data Index: 1028471 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.1945. Min Act: -0.1700
Data Index: 8645949 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.1945. Min Act: -0.1700
Data Index: 3963255 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0695. Min Act: -0.1700
Data Index: 1408540 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0695. Min Act: -0.1700
Data Index: 463456 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0695. Min Act: -0.1700
Data Index: 7401409 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0695. Min Act: -0.1700
Data Index: 7115213 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0070. Min Act: -0.1700
Data Index: 5117243 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0070. Min Act: -0.1700
Data Index: 5941340 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0070. Min Act: -0.1700
Data Index: 6187295 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0070. Min Act: -0.1700
Data Index: 831166 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8195. Min Range: -9.8195
Max Act: 9.0070. Min Act: -0.1700
Data Index: 8389475 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19