Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.8498. Min Act: -0.1700
Data Index: 6861735 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.4123. Min Act: -0.1700
Data Index: 6293864 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.4123. Min Act: -0.1700
Data Index: 4272416 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.3185. Min Act: -0.1700
Data Index: 4893302 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2873. Min Act: -0.1700
Data Index: 4417638 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2560. Min Act: -0.1700
Data Index: 3144685 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2873. Min Act: -0.1700
Data Index: 1781371 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2248. Min Act: -0.1700
Data Index: 2691440 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2248. Min Act: -0.1700
Data Index: 8552726 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2248. Min Act: -0.1700
Data Index: 6750687 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.2248. Min Act: -0.1700
Data Index: 8552725 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.1935. Min Act: -0.1700
Data Index: 3397653 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.1935. Min Act: -0.1700
Data Index: 4492111 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.1623. Min Act: -0.1700
Data Index: 339881 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.1310. Min Act: -0.1700
Data Index: 7320178 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.1310. Min Act: -0.1700
Data Index: 384239 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.0998. Min Act: -0.1700
Data Index: 4097871 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.0998. Min Act: -0.1700
Data Index: 491889 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.0685. Min Act: -0.1700
Data Index: 6247669 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8498. Min Range: -6.8498
Max Act: 6.0998. Min Act: -0.1700
Data Index: 1948005 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19