Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2484. Min Range: -8.2484
Max Act: 8.2484. Min Act: -0.1700
Data Index: 3854124 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2484. Min Range: -8.2484
Max Act: 8.0296. Min Act: -0.1700
Data Index: 6018909 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.9359. Min Act: -0.1700
Data Index: 8121335 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.7796. Min Act: -0.1700
Data Index: 6338208 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.7796. Min Act: -0.1700
Data Index: 5661958 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.7171. Min Act: -0.1700
Data Index: 3540728 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.6859. Min Act: -0.1700
Data Index: 8763398 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.6859. Min Act: -0.1700
Data Index: 2707648 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.6234. Min Act: -0.1700
Data Index: 6154147 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.6546. Min Act: -0.1700
Data Index: 5263375 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.5296. Min Act: -0.1700
Data Index: 8742266 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.5296. Min Act: -0.1700
Data Index: 4066667 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4984. Min Act: -0.1700
Data Index: 7241798 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4359. Min Act: -0.1700
Data Index: 4174419 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4671. Min Act: -0.1700
Data Index: 5435479 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4671. Min Act: -0.1700
Data Index: 3739643 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4359. Min Act: -0.1700
Data Index: 7400584 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4671. Min Act: -0.1700
Data Index: 4298842 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4359. Min Act: -0.1700
Data Index: 258275 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2484. Min Range: -8.2484
Max Act: 7.4359. Min Act: -0.1700
Data Index: 6655023 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19