Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7678. Min Act: -0.1700
Data Index: 3119530 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4706963 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7366. Min Act: -0.1700
Data Index: 6252087 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7366. Min Act: -0.1700
Data Index: 3092047 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7053. Min Act: -0.1700
Data Index: 4706962 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5803. Min Act: -0.1700
Data Index: 204089 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 1627023 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5178. Min Act: -0.1700
Data Index: 3218125 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4866. Min Act: -0.1700
Data Index: 8132797 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4866. Min Act: -0.1700
Data Index: 6851926 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4866. Min Act: -0.1700
Data Index: 5614683 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4866. Min Act: -0.1700
Data Index: 2356759 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4241. Min Act: -0.1700
Data Index: 8389874 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4773347 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.4553. Min Act: -0.1700
Data Index: 8056389 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.3928. Min Act: -0.1700
Data Index: 2915564 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.3928. Min Act: -0.1700
Data Index: 4676279 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.3928. Min Act: -0.1700
Data Index: 2466953 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.3928. Min Act: -0.1700
Data Index: 885835 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.3928. Min Act: -0.1700
Data Index: 7270438 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19