Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5513. Min Range: -10.5513
Max Act: 10.5513. Min Act: -0.1700
Data Index: 6729506 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5513. Min Range: -10.5513
Max Act: 10.4263. Min Act: -0.1700
Data Index: 6729497 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5513. Min Range: -10.5513
Max Act: 10.1763. Min Act: -0.1700
Data Index: 1789668 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.9263. Min Act: -0.1700
Data Index: 5418972 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.8013. Min Act: -0.1700
Data Index: 8759820 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.6763. Min Act: -0.1700
Data Index: 6781757 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.6763. Min Act: -0.1700
Data Index: 1781676 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.6138. Min Act: -0.1700
Data Index: 4291834 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.5513. Min Act: -0.1700
Data Index: 5015099 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.4263. Min Act: -0.1700
Data Index: 4512694 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.4263. Min Act: -0.1700
Data Index: 3782753 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.3638. Min Act: -0.1700
Data Index: 6077343 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.3638. Min Act: -0.1700
Data Index: 5695289 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.4263. Min Act: -0.1700
Data Index: 5104602 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.3013. Min Act: -0.1700
Data Index: 5062772 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.2388. Min Act: -0.1700
Data Index: 1554047 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.2388. Min Act: -0.1700
Data Index: 8474687 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.1763. Min Act: -0.1700
Data Index: 5972242 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.1763. Min Act: -0.1700
Data Index: 886381 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5513. Min Range: -10.5513
Max Act: 9.1763. Min Act: -0.1700
Data Index: 2900289 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19