Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0651. Min Range: -7.0651
Max Act: 7.0651. Min Act: -0.1700
Data Index: 1272763 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.7526. Min Act: -0.1700
Data Index: 3454584 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.7526. Min Act: -0.1700
Data Index: 617283 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.7213. Min Act: -0.1700
Data Index: 5149316 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.6901. Min Act: -0.1700
Data Index: 525118 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.6276. Min Act: -0.1700
Data Index: 69577 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.5651. Min Act: -0.1700
Data Index: 4841925 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.5338. Min Act: -0.1700
Data Index: 8190896 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.5026. Min Act: -0.1700
Data Index: 8752842 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4713. Min Act: -0.1700
Data Index: 7504686 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4713. Min Act: -0.1700
Data Index: 2641300 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4401. Min Act: -0.1700
Data Index: 1276261 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4088. Min Act: -0.1700
Data Index: 4882166 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4401. Min Act: -0.1700
Data Index: 3686535 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4401. Min Act: -0.1700
Data Index: 5110686 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4401. Min Act: -0.1700
Data Index: 261851 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4401. Min Act: -0.1700
Data Index: 6752831 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4088. Min Act: -0.1700
Data Index: 6539688 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4088. Min Act: -0.1700
Data Index: 2655639 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0651. Min Range: -7.0651
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5511040 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19