Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 610 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.3936. Min Act: -0.1700
Data Index: 7328110 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2998. Min Act: -0.1700
Data Index: 355648 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2998. Min Act: -0.1700
Data Index: 7171299 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2686. Min Act: -0.1700
Data Index: 8751402 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2686. Min Act: -0.1700
Data Index: 6274286 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2686. Min Act: -0.1700
Data Index: 3115042 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2686. Min Act: -0.1700
Data Index: 4803621 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2373. Min Act: -0.1700
Data Index: 8715839 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2373. Min Act: -0.1700
Data Index: 3189789 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2373. Min Act: -0.1700
Data Index: 6691641 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2060. Min Act: -0.1700
Data Index: 2534030 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.2060. Min Act: -0.1700
Data Index: 1555204 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1123. Min Act: -0.1700
Data Index: 453606 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1435. Min Act: -0.1700
Data Index: 6706830 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1123. Min Act: -0.1700
Data Index: 2231039 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1123. Min Act: -0.1700
Data Index: 3456368 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1123. Min Act: -0.1700
Data Index: 7781356 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1123. Min Act: -0.1700
Data Index: 6323936 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.1435. Min Act: -0.1700
Data Index: 1693763 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3936. Min Range: -4.3936
Max Act: 4.0810. Min Act: -0.1700
Data Index: 3000888 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19