Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1354. Min Range: -8.1354
Max Act: 8.1354. Min Act: -0.1700
Data Index: 853451 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1354. Min Range: -8.1354
Max Act: 8.0729. Min Act: -0.1700
Data Index: 3373022 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.9479. Min Act: -0.1700
Data Index: 7099023 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.8541. Min Act: -0.1700
Data Index: 938557 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.8229. Min Act: -0.1700
Data Index: 8702342 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.7916. Min Act: -0.1700
Data Index: 4055632 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.6979. Min Act: -0.1700
Data Index: 3347827 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.5104. Min Act: -0.1700
Data Index: 6842344 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.5104. Min Act: -0.1700
Data Index: 4355970 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 5208905 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4166. Min Act: -0.1700
Data Index: 1743157 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 4628653 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 4550610 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 1227386 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 5447693 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4479. Min Act: -0.1700
Data Index: 6565750 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.4166. Min Act: -0.1700
Data Index: 8250902 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.2916. Min Act: -0.1700
Data Index: 1619118 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.2916. Min Act: -0.1700
Data Index: 1304172 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1354. Min Range: -8.1354
Max Act: 7.2604. Min Act: -0.1700
Data Index: 3404082 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19