Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3077. Min Range: -9.3077
Max Act: 9.3077. Min Act: -0.1700
Data Index: 7193874 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3077. Min Range: -9.3077
Max Act: 9.2452. Min Act: -0.1700
Data Index: 1096334 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.9952. Min Act: -0.1700
Data Index: 5014903 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.9327. Min Act: -0.1700
Data Index: 1343720 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.8077. Min Act: -0.1700
Data Index: 7098676 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.7452. Min Act: -0.1700
Data Index: 1426469 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.7452. Min Act: -0.1700
Data Index: 2575786 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.6827. Min Act: -0.1700
Data Index: 2575797 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.6827. Min Act: -0.1700
Data Index: 8705167 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.6827. Min Act: -0.1700
Data Index: 6530956 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.6827. Min Act: -0.1700
Data Index: 2575781 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.6202. Min Act: -0.1700
Data Index: 2575793 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.5577. Min Act: -0.1700
Data Index: 4235850 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.4952. Min Act: -0.1700
Data Index: 2543348 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.4952. Min Act: -0.1700
Data Index: 1131926 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.4952. Min Act: -0.1700
Data Index: 7800748 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.4327. Min Act: -0.1700
Data Index: 1153945 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.3702. Min Act: -0.1700
Data Index: 7338093 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.3702. Min Act: -0.1700
Data Index: 6486540 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3077. Min Range: -9.3077
Max Act: 8.3702. Min Act: -0.1700
Data Index: 8180999 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19