Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.6631. Min Act: -0.1700
Data Index: 455961 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.5694. Min Act: -0.1700
Data Index: 3665136 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.5069. Min Act: -0.1700
Data Index: 3858769 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.5069. Min Act: -0.1700
Data Index: 3864529 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.4756. Min Act: -0.1700
Data Index: 8414657 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.4131. Min Act: -0.1700
Data Index: 5024674 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2881. Min Act: -0.1700
Data Index: 6884594 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2881. Min Act: -0.1700
Data Index: 7295339 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2569. Min Act: -0.1700
Data Index: 95538 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2569. Min Act: -0.1700
Data Index: 738365 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2569. Min Act: -0.1700
Data Index: 4344143 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2256. Min Act: -0.1700
Data Index: 7560808 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3483311 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1944. Min Act: -0.1700
Data Index: 2362115 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5611505 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3257715 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1319. Min Act: -0.1700
Data Index: 4484022 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1006. Min Act: -0.1700
Data Index: 7632206 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0381. Min Act: -0.1700
Data Index: 959020 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0069. Min Act: -0.1700
Data Index: 544436 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19