Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5630 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.8863. Min Act: -0.1700
Data Index: 6710406 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.8550. Min Act: -0.1700
Data Index: 4013964 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.7925. Min Act: -0.1700
Data Index: 797941 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.8238. Min Act: -0.1700
Data Index: 8822070 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.8238. Min Act: -0.1700
Data Index: 5044985 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.7925. Min Act: -0.1700
Data Index: 1434161 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.7613. Min Act: -0.1700
Data Index: 5887024 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.7613. Min Act: -0.1700
Data Index: 1335975 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.7613. Min Act: -0.1700
Data Index: 2290182 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.6988. Min Act: -0.1700
Data Index: 7347100 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.6988. Min Act: -0.1700
Data Index: 6504086 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.6675. Min Act: -0.1700
Data Index: 5464080 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.6675. Min Act: -0.1700
Data Index: 7731967 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.5738. Min Act: -0.1700
Data Index: 2220724 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.5738. Min Act: -0.1700
Data Index: 7658506 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.5113. Min Act: -0.1700
Data Index: 2995531 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.5113. Min Act: -0.1700
Data Index: 2070910 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.4800. Min Act: -0.1700
Data Index: 2040190 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.4800. Min Act: -0.1700
Data Index: 5666658 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8863. Min Range: -6.8863
Max Act: 6.4800. Min Act: -0.1700
Data Index: 3623146 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19