Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4327 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.3585. Min Act: -0.1700
Data Index: 3977817 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.3585. Min Act: -0.1700
Data Index: 3945622 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2960. Min Act: -0.1700
Data Index: 1215528 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2960. Min Act: -0.1700
Data Index: 225734 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2960. Min Act: -0.1700
Data Index: 5747358 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2960. Min Act: -0.1700
Data Index: 5086304 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.1710. Min Act: -0.1700
Data Index: 918774 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 8810378 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 3350153 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 2322064 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 5173695 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 8495717 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 225731 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.2335. Min Act: -0.1700
Data Index: 4777461 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.1710. Min Act: -0.1700
Data Index: 5471971 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.1085. Min Act: -0.1700
Data Index: 5589221 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.1085. Min Act: -0.1700
Data Index: 3759473 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.0460. Min Act: -0.1700
Data Index: 2436894 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.1085. Min Act: -0.1700
Data Index: 4649923 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3585. Min Range: -9.3585
Max Act: 9.0460. Min Act: -0.1700
Data Index: 1186954 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19