Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8997. Min Act: -0.1700
Data Index: 1265104 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8685. Min Act: -0.1700
Data Index: 5633987 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8372. Min Act: -0.1700
Data Index: 608534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8372. Min Act: -0.1700
Data Index: 1577298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8372. Min Act: -0.1700
Data Index: 7721556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8059. Min Act: -0.1700
Data Index: 2999223 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8059. Min Act: -0.1700
Data Index: 3622013 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8059. Min Act: -0.1700
Data Index: 7696980 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.8059. Min Act: -0.1700
Data Index: 1499318 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7747. Min Act: -0.1700
Data Index: 2326339 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7747. Min Act: -0.1700
Data Index: 1886339 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7747. Min Act: -0.1700
Data Index: 5034508 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7747. Min Act: -0.1700
Data Index: 914037 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7747. Min Act: -0.1700
Data Index: 5691377 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 3284833 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 3362721 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 3439095 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 1102346 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 4069273 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8997. Min Range: -3.8997
Max Act: 3.7434. Min Act: -0.1700
Data Index: 4770430 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19