Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1986 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.6541. Min Act: -0.1700
Data Index: 2846066 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.6229. Min Act: -0.1700
Data Index: 1419572 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5916. Min Act: -0.1700
Data Index: 3292805 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5604. Min Act: -0.1700
Data Index: 8331684 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5604. Min Act: -0.1700
Data Index: 6666405 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5604. Min Act: -0.1700
Data Index: 8592860 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5291. Min Act: -0.1700
Data Index: 2191205 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5291. Min Act: -0.1700
Data Index: 3688753 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5291. Min Act: -0.1700
Data Index: 947353 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.5291. Min Act: -0.1700
Data Index: 2276892 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5653592 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4979. Min Act: -0.1700
Data Index: 7775397 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 6749927 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 7964238 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 3613564 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 5634078 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 7831992 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4666. Min Act: -0.1700
Data Index: 1139189 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4354. Min Act: -0.1700
Data Index: 8522714 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6541. Min Range: -4.6541
Max Act: 4.4354. Min Act: -0.1700
Data Index: 7831996 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19