Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.3943. Min Act: -0.1700
Data Index: 4418301 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.3943. Min Act: -0.1700
Data Index: 2187446 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.3943. Min Act: -0.1700
Data Index: 4921355 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.3318. Min Act: -0.1700
Data Index: 4007525 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.3318. Min Act: -0.1700
Data Index: 2615659 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.2693. Min Act: -0.1700
Data Index: 7719379 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.2693. Min Act: -0.1700
Data Index: 3686885 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.2380. Min Act: -0.1700
Data Index: 1521599 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.1755. Min Act: -0.1700
Data Index: 3531625 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.1443. Min Act: -0.1700
Data Index: 2714775 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.1443. Min Act: -0.1700
Data Index: 2068337 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.1130. Min Act: -0.1700
Data Index: 1542639 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.1130. Min Act: -0.1700
Data Index: 2501986 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.0818. Min Act: -0.1700
Data Index: 319857 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.0818. Min Act: -0.1700
Data Index: 7149581 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.0505. Min Act: -0.1700
Data Index: 3605997 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.0193. Min Act: -0.1700
Data Index: 5863418 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3943. Min Range: -6.3943
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2318150 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3943. Min Range: -6.3943
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1902832 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3943. Min Range: -6.3943
Max Act: 5.9880. Min Act: -0.1700
Data Index: 711556 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19