Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.7533. Min Act: -0.1700
Data Index: 1599974 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.7533. Min Act: -0.1700
Data Index: 7681128 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6050221 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.5971. Min Act: -0.1700
Data Index: 8104425 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.5346. Min Act: -0.1700
Data Index: 6676015 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.5658. Min Act: -0.1700
Data Index: 8367782 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.5033. Min Act: -0.1700
Data Index: 1505200 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4721. Min Act: -0.1700
Data Index: 4684823 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 7836799 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4721. Min Act: -0.1700
Data Index: 242701 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4721. Min Act: -0.1700
Data Index: 5535303 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4721. Min Act: -0.1700
Data Index: 6872649 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4721. Min Act: -0.1700
Data Index: 4652792 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 6628605 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 6449063 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 7771674 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4096. Min Act: -0.1700
Data Index: 303378 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4096. Min Act: -0.1700
Data Index: 6870260 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 1853744 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7533. Min Range: -5.7533
Max Act: 5.3783. Min Act: -0.1700
Data Index: 6329657 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19