Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 937 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4970. Min Range: -8.4970
Max Act: 8.4970. Min Act: -0.1700
Data Index: 2838357 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.8095. Min Act: -0.1700
Data Index: 4305829 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.6220. Min Act: -0.1700
Data Index: 4667084 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.5908. Min Act: -0.1700
Data Index: 4257860 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.5908. Min Act: -0.1700
Data Index: 3468887 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.5908. Min Act: -0.1700
Data Index: 2233732 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4970. Min Act: -0.1700
Data Index: 6821239 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4970. Min Act: -0.1700
Data Index: 592995 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4970. Min Act: -0.1700
Data Index: 6607860 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4658. Min Act: -0.1700
Data Index: 5410194 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4033. Min Act: -0.1700
Data Index: 2948385 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.4033. Min Act: -0.1700
Data Index: 4153424 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3720. Min Act: -0.1700
Data Index: 1978959 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3720. Min Act: -0.1700
Data Index: 1537776 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3720. Min Act: -0.1700
Data Index: 4176978 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3720. Min Act: -0.1700
Data Index: 6401054 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3408. Min Act: -0.1700
Data Index: 267569 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3095. Min Act: -0.1700
Data Index: 1216706 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3408. Min Act: -0.1700
Data Index: 4452145 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4970. Min Range: -8.4970
Max Act: 7.3408. Min Act: -0.1700
Data Index: 2790275 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19