Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.6933. Min Act: -0.1700
Data Index: 4473436 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.3808. Min Act: -0.1700
Data Index: 7498436 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.3183. Min Act: -0.1700
Data Index: 4180018 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.2871. Min Act: -0.1700
Data Index: 5744413 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.2558. Min Act: -0.1700
Data Index: 1897327 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.2246. Min Act: -0.1700
Data Index: 6692806 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1621. Min Act: -0.1700
Data Index: 305687 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 5342319 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 6947061 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7177565 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 671271 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 348911 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0996. Min Act: -0.1700
Data Index: 3189338 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0996. Min Act: -0.1700
Data Index: 664283 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.1308. Min Act: -0.1700
Data Index: 2443582 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0996. Min Act: -0.1700
Data Index: 2451736 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0683. Min Act: -0.1700
Data Index: 1166411 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0683. Min Act: -0.1700
Data Index: 4002109 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0683. Min Act: -0.1700
Data Index: 1077364 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6933. Min Range: -6.6933
Max Act: 6.0371. Min Act: -0.1700
Data Index: 6323774 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19