Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0651. Min Range: -8.0651
Max Act: 8.0651. Min Act: -0.1700
Data Index: 57923 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.8463. Min Act: -0.1700
Data Index: 4707129 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.7526. Min Act: -0.1700
Data Index: 7876017 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6901. Min Act: -0.1700
Data Index: 2840419 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6276. Min Act: -0.1700
Data Index: 818992 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5651. Min Act: -0.1700
Data Index: 7371552 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4713. Min Act: -0.1700
Data Index: 6174676 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5026. Min Act: -0.1700
Data Index: 1349452 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4713. Min Act: -0.1700
Data Index: 5483386 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4713. Min Act: -0.1700
Data Index: 228497 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4088. Min Act: -0.1700
Data Index: 1559901 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4088. Min Act: -0.1700
Data Index: 228968 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.4088. Min Act: -0.1700
Data Index: 3223230 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3776. Min Act: -0.1700
Data Index: 3571035 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3776. Min Act: -0.1700
Data Index: 1063570 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3463. Min Act: -0.1700
Data Index: 2338266 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3463. Min Act: -0.1700
Data Index: 131278 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3151. Min Act: -0.1700
Data Index: 3719997 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.3151. Min Act: -0.1700
Data Index: 6582216 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.2838. Min Act: -0.1700
Data Index: 7739905 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19