Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1538. Min Range: -8.1538
Max Act: 8.1538. Min Act: -0.1700
Data Index: 562416 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.7163. Min Act: -0.1700
Data Index: 6299782 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.7163. Min Act: -0.1700
Data Index: 4449962 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.6538. Min Act: -0.1700
Data Index: 5767148 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.6538. Min Act: -0.1700
Data Index: 6322071 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.5288. Min Act: -0.1700
Data Index: 6577032 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.5288. Min Act: -0.1700
Data Index: 7082637 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.5288. Min Act: -0.1700
Data Index: 6488880 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.5288. Min Act: -0.1700
Data Index: 7583881 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4975. Min Act: -0.1700
Data Index: 6605736 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4663. Min Act: -0.1700
Data Index: 8154695 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4350. Min Act: -0.1700
Data Index: 5632008 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4350. Min Act: -0.1700
Data Index: 2661151 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4038. Min Act: -0.1700
Data Index: 3685165 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4038. Min Act: -0.1700
Data Index: 856149 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.4038. Min Act: -0.1700
Data Index: 6858790 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.3413. Min Act: -0.1700
Data Index: 7515278 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.3413. Min Act: -0.1700
Data Index: 6629774 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.3100. Min Act: -0.1700
Data Index: 8014454 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1538. Min Range: -8.1538
Max Act: 7.3413. Min Act: -0.1700
Data Index: 6376685 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19