Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2088. Min Range: -8.2088
Max Act: 8.2088. Min Act: -0.1699
Data Index: 5443601 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.9588. Min Act: -0.1643
Data Index: 3560455 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.9588. Min Act: -0.1700
Data Index: 4015107 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.8338. Min Act: -0.1694
Data Index: 8484871 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.8338. Min Act: -0.1700
Data Index: 4015095 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.8338. Min Act: -0.1698
Data Index: 4015113 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.7713. Min Act: -0.1683
Data Index: 5443589 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.7713. Min Act: -0.1650
Data Index: 2710555 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.7713. Min Act: -0.1700
Data Index: 6366509 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.7088. Min Act: -0.1700
Data Index: 889824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.7088. Min Act: -0.1695
Data Index: 7533338 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.6463. Min Act: -0.1693
Data Index: 1606644 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.6463. Min Act: -0.1700
Data Index: 6612119 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.6463. Min Act: -0.1700
Data Index: 2710559 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.6463. Min Act: -0.1700
Data Index: 6209039 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.6463. Min Act: -0.0836
Data Index: 373449 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.5838. Min Act: -0.1556
Data Index: 4970900 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.5838. Min Act: -0.1700
Data Index: 3378126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.5838. Min Act: -0.1697
Data Index: 5443600 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2088. Min Range: -8.2088
Max Act: 7.5838. Min Act: -0.1289
Data Index: 3605292 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19