Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 367 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.4952. Min Act: -0.1700
Data Index: 292624 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2913. Min Act: -0.1700
Data Index: 2021122 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2285. Min Act: -0.1700
Data Index: 5079020 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2285. Min Act: -0.1700
Data Index: 677117 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2128. Min Act: -0.1700
Data Index: 53817 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2128. Min Act: -0.1700
Data Index: 4848974 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.2128. Min Act: -0.1700
Data Index: 4103946 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1813. Min Act: -0.1700
Data Index: 7068103 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1971. Min Act: -0.1700
Data Index: 3335188 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1656. Min Act: -0.1700
Data Index: 5219137 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1656. Min Act: -0.1700
Data Index: 5645021 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1499. Min Act: -0.1700
Data Index: 4945673 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1341. Min Act: -0.1700
Data Index: 3335186 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 6722670 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 2210546 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 1079874 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 7271230 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 8294646 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 3803890 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4952. Min Range: -3.4952
Max Act: 3.1026. Min Act: -0.1700
Data Index: 6599099 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19