Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0958. Min Range: -7.0958
Max Act: 7.0958. Min Act: -0.1700
Data Index: 2675417 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0958. Min Range: -7.0958
Max Act: 7.0645. Min Act: -0.1700
Data Index: 7991723 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0958. Min Range: -7.0958
Max Act: 7.0020. Min Act: -0.1700
Data Index: 8304695 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.9395. Min Act: -0.1700
Data Index: 7669050 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.8458. Min Act: -0.1700
Data Index: 7077361 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.8145. Min Act: -0.1700
Data Index: 3296105 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.8145. Min Act: -0.1700
Data Index: 6356909 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7833. Min Act: -0.1700
Data Index: 1145634 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7833. Min Act: -0.1700
Data Index: 4954823 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6175422 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7520. Min Act: -0.1700
Data Index: 4869002 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7520. Min Act: -0.1700
Data Index: 1152859 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7208. Min Act: -0.1700
Data Index: 3050857 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7208. Min Act: -0.1700
Data Index: 4736258 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7208. Min Act: -0.1700
Data Index: 2610234 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.7208. Min Act: -0.1700
Data Index: 5858127 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.6583. Min Act: -0.1700
Data Index: 6154172 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.6583. Min Act: -0.1700
Data Index: 6391122 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.6583. Min Act: -0.1700
Data Index: 2282946 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0958. Min Range: -7.0958
Max Act: 6.6583. Min Act: -0.1700
Data Index: 3489691 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19