Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9921. Min Act: -0.1700
Data Index: 154388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9609. Min Act: -0.1700
Data Index: 854977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9609. Min Act: -0.1700
Data Index: 5999064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9609. Min Act: -0.1700
Data Index: 2097247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3780467 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9296. Min Act: -0.1700
Data Index: 8166784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.9296. Min Act: -0.1700
Data Index: 99676 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 5666691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 6424596 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 2704108 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 4735390 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 4306733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8983. Min Act: -0.1700
Data Index: 293670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8358. Min Act: -0.1699
Data Index: 541121 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 4414051 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 744044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 4458273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 791927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 1544383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9921. Min Range: -3.9921
Max Act: 3.8671. Min Act: -0.1700
Data Index: 375257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19