Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.3435. Min Act: -0.1700
Data Index: 3798128 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.2498. Min Act: -0.1700
Data Index: 1353438 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.2498. Min Act: -0.1700
Data Index: 6504400 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.1248. Min Act: -0.1700
Data Index: 6571984 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.0622. Min Act: -0.1700
Data Index: 1369672 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3435. Min Range: -4.3435
Max Act: 4.0622. Min Act: -0.1700
Data Index: 6874791 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9997. Min Act: -0.1700
Data Index: 6865828 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9997. Min Act: -0.1700
Data Index: 6749560 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9997. Min Act: -0.1700
Data Index: 2654508 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9997. Min Act: -0.1700
Data Index: 805696 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9685. Min Act: -0.1700
Data Index: 4158197 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9372. Min Act: -0.1698
Data Index: 5156395 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1497204 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.8747. Min Act: -0.1700
Data Index: 3615633 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1105034 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.8434. Min Act: -0.1700
Data Index: 6111769 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.8434. Min Act: -0.1700
Data Index: 7655657 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.7809. Min Act: -0.1700
Data Index: 1207009 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.7496. Min Act: -0.1700
Data Index: 4417665 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3435. Min Range: -4.3435
Max Act: 3.7496. Min Act: -0.1700
Data Index: 5014619 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19