Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1637 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1343. Min Range: -10.1343
Max Act: 10.1343. Min Act: -0.1700
Data Index: 7779589 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1343. Min Range: -10.1343
Max Act: 10.0093. Min Act: -0.1700
Data Index: 717001 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.8843. Min Act: -0.1700
Data Index: 880292 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.6968. Min Act: -0.1700
Data Index: 1229042 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.6968. Min Act: -0.1700
Data Index: 3328959 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.6343. Min Act: -0.1700
Data Index: 4674545 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.5718. Min Act: -0.1700
Data Index: 7658125 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.5093. Min Act: -0.1700
Data Index: 3179873 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.5093. Min Act: -0.1700
Data Index: 3240203 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.5093. Min Act: -0.1700
Data Index: 5911191 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.5093. Min Act: -0.1700
Data Index: 3062766 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.4468. Min Act: -0.1700
Data Index: 220317 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.4468. Min Act: -0.1700
Data Index: 2066761 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.4468. Min Act: -0.1700
Data Index: 2772902 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.3843. Min Act: -0.1700
Data Index: 446584 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.3843. Min Act: -0.1700
Data Index: 1953014 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.3843. Min Act: -0.1700
Data Index: 4970123 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.3843. Min Act: -0.1700
Data Index: 5185244 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.3843. Min Act: -0.1700
Data Index: 7431953 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1343. Min Range: -10.1343
Max Act: 9.2593. Min Act: -0.1700
Data Index: 7334638 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19