Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2540 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.3558. Min Act: -0.1700
Data Index: 4582624 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.2621. Min Act: -0.1700
Data Index: 7352026 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.2933. Min Act: -0.1700
Data Index: 2671410 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.1683. Min Act: -0.1700
Data Index: 733254 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0746. Min Act: -0.1700
Data Index: 5678549 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0746. Min Act: -0.1700
Data Index: 4595097 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0433. Min Act: -0.1700
Data Index: 4944720 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0121. Min Act: -0.1700
Data Index: 4490740 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0121. Min Act: -0.1700
Data Index: 8517658 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0121. Min Act: -0.1700
Data Index: 4007409 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9808. Min Act: -0.1700
Data Index: 6489229 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9808. Min Act: -0.1700
Data Index: 3513899 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9496. Min Act: -0.1700
Data Index: 5308242 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 75934 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9496. Min Act: -0.1700
Data Index: 2851093 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 8215658 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 3849340 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 4060953 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8871. Min Act: -0.1700
Data Index: 6528622 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 3123845 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19