Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.9257. Min Act: -0.1700
Data Index: 8163998 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.8944. Min Act: -0.1700
Data Index: 4160061 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.8631. Min Act: -0.1700
Data Index: 8231715 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.8319. Min Act: -0.1700
Data Index: 1453703 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.7693. Min Act: -0.1700
Data Index: 6870764 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.7380. Min Act: -0.1700
Data Index: 642949 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.7224. Min Act: -0.1700
Data Index: 2244183 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.7224. Min Act: -0.1700
Data Index: 5684905 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.7068. Min Act: -0.1700
Data Index: 5812850 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6755. Min Act: -0.1700
Data Index: 2424820 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6755. Min Act: -0.1700
Data Index: 4925443 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6442. Min Act: -0.1700
Data Index: 4144010 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6129. Min Act: -0.1700
Data Index: 388661 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6285. Min Act: -0.1700
Data Index: 5117416 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.6285. Min Act: -0.1700
Data Index: 1099580 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.5816. Min Act: -0.1700
Data Index: 1994169 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.5816. Min Act: -0.1700
Data Index: 6571329 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.5972. Min Act: -0.1700
Data Index: 8761503 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.5816. Min Act: -0.1700
Data Index: 2675709 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9257. Min Range: -3.9257
Max Act: 3.5816. Min Act: -0.1700
Data Index: 384798 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19