Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2977. Min Range: -8.2977
Max Act: 8.2977. Min Act: -0.1700
Data Index: 5294090 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2977. Min Range: -8.2977
Max Act: 8.0477. Min Act: -0.1700
Data Index: 519406 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2977. Min Range: -8.2977
Max Act: 8.0477. Min Act: -0.1700
Data Index: 1363714 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 3315018 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7977. Min Act: -0.1700
Data Index: 1400718 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 4110203 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 3793895 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 1650056 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 3941387 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 7074586 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 3090536 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.7977. Min Act: -0.1700
Data Index: 7527453 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 4445295 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 8702038 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 4557953 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 3185187 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 8815103 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6102. Min Act: -0.1700
Data Index: 8576309 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.6102. Min Act: -0.1700
Data Index: 3465631 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2977. Min Range: -8.2977
Max Act: 7.5477. Min Act: -0.1700
Data Index: 4683074 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19