Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.3902. Min Act: -0.1700
Data Index: 3539398 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.3277. Min Act: -0.1700
Data Index: 5522202 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.3277. Min Act: -0.1700
Data Index: 795027 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.2965. Min Act: -0.1700
Data Index: 7600670 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.2340. Min Act: -0.1700
Data Index: 919319 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.1402. Min Act: -0.1700
Data Index: 7953194 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.1402. Min Act: -0.1700
Data Index: 7693316 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.1090. Min Act: -0.1700
Data Index: 5031873 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0777. Min Act: -0.1700
Data Index: 8485743 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0777. Min Act: -0.1700
Data Index: 4075878 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0465. Min Act: -0.1700
Data Index: 2044522 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0465. Min Act: -0.1700
Data Index: 1785461 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0152. Min Act: -0.1700
Data Index: 1608727 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0465. Min Act: -0.1700
Data Index: 2327579 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3902. Min Range: -7.3902
Max Act: 7.0152. Min Act: -0.1700
Data Index: 7238626 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3902. Min Range: -7.3902
Max Act: 6.9527. Min Act: -0.1700
Data Index: 3840270 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3902. Min Range: -7.3902
Max Act: 6.9527. Min Act: -0.1700
Data Index: 1447962 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3902. Min Range: -7.3902
Max Act: 6.9527. Min Act: -0.1700
Data Index: 6365868 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3902. Min Range: -7.3902
Max Act: 6.9215. Min Act: -0.1700
Data Index: 1373667 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3902. Min Range: -7.3902
Max Act: 6.9215. Min Act: -0.1700
Data Index: 6725811 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19