Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0649. Min Range: -7.0649
Max Act: 7.0649. Min Act: -0.1700
Data Index: 1994795 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.9087. Min Act: -0.1700
Data Index: 4419858 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.8774. Min Act: -0.1700
Data Index: 8821490 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7515329 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.7837. Min Act: -0.1700
Data Index: 478447 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.7212. Min Act: -0.1700
Data Index: 1804207 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1103525 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.6274. Min Act: -0.1700
Data Index: 7774054 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5962. Min Act: -0.1700
Data Index: 6677168 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5962. Min Act: -0.1700
Data Index: 2542616 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5962. Min Act: -0.1700
Data Index: 5927142 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5337. Min Act: -0.1700
Data Index: 2618300 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4122696 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.5024. Min Act: -0.1700
Data Index: 2904258 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.4712. Min Act: -0.1700
Data Index: 1539971 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.4399. Min Act: -0.1700
Data Index: 217284 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 1993040 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 1865294 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.3462. Min Act: -0.1700
Data Index: 6895891 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0649. Min Range: -7.0649
Max Act: 6.3149. Min Act: -0.1700
Data Index: 3791826 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19