Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.3172. Min Act: -0.1700
Data Index: 8301807 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.2860. Min Act: -0.1700
Data Index: 6052981 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.2547. Min Act: -0.1700
Data Index: 3692190 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.1610. Min Act: -0.1700
Data Index: 4581715 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.1297. Min Act: -0.1700
Data Index: 3044958 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.1297. Min Act: -0.1700
Data Index: 7875653 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.1297. Min Act: -0.1700
Data Index: 2144044 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0672. Min Act: -0.1700
Data Index: 6400649 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0672. Min Act: -0.1700
Data Index: 5822504 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0359. Min Act: -0.1700
Data Index: 6508377 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0359. Min Act: -0.1700
Data Index: 8696772 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0359. Min Act: -0.1700
Data Index: 1060255 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0047. Min Act: -0.1700
Data Index: 5176183 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3172. Min Range: -4.3172
Max Act: 4.0047. Min Act: -0.1700
Data Index: 7645714 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9734. Min Act: -0.1700
Data Index: 7218571 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9734. Min Act: -0.1700
Data Index: 6006426 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9109. Min Act: -0.1700
Data Index: 7269398 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9109. Min Act: -0.1700
Data Index: 1907332 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9109. Min Act: -0.1700
Data Index: 7380714 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3172. Min Range: -4.3172
Max Act: 3.9109. Min Act: -0.1700
Data Index: 6356061 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19