Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1570. Min Act: -0.1700
Data Index: 1371244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1570. Min Act: -0.1700
Data Index: 7763548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1403. Min Act: -0.1700
Data Index: 5172366 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1403. Min Act: -0.1700
Data Index: 642991 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 8141122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 3723000 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 8678855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 8645413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 8424963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 2248566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 7546661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 7222034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 4009692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 3611578 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1236. Min Act: -0.1700
Data Index: 4870030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 2665224 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 2249148 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 4438187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 4456007 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1570. Min Range: -2.1570
Max Act: 2.1069. Min Act: -0.1700
Data Index: 4571816 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19