Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5894. Min Range: -7.5894
Max Act: 7.5894. Min Act: -0.1700
Data Index: 3648342 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.9019. Min Act: -0.1700
Data Index: 254829 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.8707. Min Act: -0.1700
Data Index: 5770403 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.8394. Min Act: -0.1700
Data Index: 5998335 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.7769. Min Act: -0.1700
Data Index: 519101 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.7144. Min Act: -0.1700
Data Index: 908248 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1867607 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.6832. Min Act: -0.1700
Data Index: 2461328 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.6519. Min Act: -0.1700
Data Index: 1894045 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.6207. Min Act: -0.1700
Data Index: 1678320 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.5582. Min Act: -0.1700
Data Index: 3262359 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.5269. Min Act: -0.1700
Data Index: 1595394 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4957. Min Act: -0.1700
Data Index: 414853 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4644. Min Act: -0.1700
Data Index: 4948784 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4644. Min Act: -0.1700
Data Index: 1031215 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4019. Min Act: -0.1700
Data Index: 4056327 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4019. Min Act: -0.1700
Data Index: 7972040 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.4019. Min Act: -0.1700
Data Index: 878271 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.3394. Min Act: -0.1700
Data Index: 6590800 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5894. Min Range: -7.5894
Max Act: 6.3394. Min Act: -0.1700
Data Index: 8553340 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19