Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4238 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2507. Min Range: -9.2507
Max Act: 9.2507. Min Act: -0.1700
Data Index: 3184873 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2507. Min Range: -9.2507
Max Act: 9.1257. Min Act: -0.1700
Data Index: 8324424 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.8757. Min Act: -0.1700
Data Index: 4293331 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.8757. Min Act: -0.1700
Data Index: 2876612 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.8132. Min Act: -0.1700
Data Index: 6120289 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.6882. Min Act: -0.1700
Data Index: 2790416 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5632. Min Act: -0.1700
Data Index: 660630 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5632. Min Act: -0.1700
Data Index: 7947790 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5632. Min Act: -0.1700
Data Index: 5293400 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5007. Min Act: -0.1700
Data Index: 5552583 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5632. Min Act: -0.1700
Data Index: 8487227 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.5007. Min Act: -0.1700
Data Index: 3048885 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.3757. Min Act: -0.1700
Data Index: 588223 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.4382. Min Act: -0.1700
Data Index: 5263826 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.4382. Min Act: -0.1700
Data Index: 2498664 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.3757. Min Act: -0.1700
Data Index: 6897194 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.3757. Min Act: -0.1700
Data Index: 4555540 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.3132. Min Act: -0.1700
Data Index: 8117138 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.2507. Min Act: -0.1700
Data Index: 6139384 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2507. Min Range: -9.2507
Max Act: 8.2507. Min Act: -0.1700
Data Index: 7789168 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19