Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6285 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0268. Min Range: -5.0268
Max Act: 5.0268. Min Act: -0.1700
Data Index: 1002386 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4638969 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.9018. Min Act: -0.1700
Data Index: 4767493 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.9018. Min Act: -0.1700
Data Index: 6297409 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 97188 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 1861073 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 5937260 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 6183003 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 8394095 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8393. Min Act: -0.1700
Data Index: 1954614 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 1673192 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 8639569 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 7196743 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3382923 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6131377 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.7768. Min Act: -0.1700
Data Index: 7543428 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.8081. Min Act: -0.1700
Data Index: 4850658 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.7768. Min Act: -0.1700
Data Index: 947767 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2163043 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0268. Min Range: -5.0268
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2227256 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19