Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4982 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0141. Min Range: -8.0141
Max Act: 8.0141. Min Act: -0.1700
Data Index: 5933047 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.7954. Min Act: -0.1700
Data Index: 6055837 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.7329. Min Act: -0.1700
Data Index: 6023652 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.6391. Min Act: -0.1700
Data Index: 3061654 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.6079. Min Act: -0.1700
Data Index: 2005154 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.6079. Min Act: -0.1700
Data Index: 5780833 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.6391. Min Act: -0.1700
Data Index: 8373736 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.5766. Min Act: -0.1700
Data Index: 2943730 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.5454. Min Act: -0.1700
Data Index: 4539635 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.4829. Min Act: -0.1700
Data Index: 8283617 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3891. Min Act: -0.1700
Data Index: 1466785 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3891. Min Act: -0.1700
Data Index: 3468736 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3579. Min Act: -0.1700
Data Index: 1670785 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3579. Min Act: -0.1700
Data Index: 718062 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3579. Min Act: -0.1700
Data Index: 4507058 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3579. Min Act: -0.1700
Data Index: 6843941 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3266. Min Act: -0.1700
Data Index: 5866324 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.3266. Min Act: -0.1700
Data Index: 5780832 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.2954. Min Act: -0.1700
Data Index: 1607 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0141. Min Range: -8.0141
Max Act: 7.2954. Min Act: -0.1700
Data Index: 7838086 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19