Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.4881. Min Act: -0.1700
Data Index: 1304631 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.3943. Min Act: -0.1700
Data Index: 2011372 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.3943. Min Act: -0.1700
Data Index: 7545005 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.3006. Min Act: -0.1700
Data Index: 5610201 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.0818. Min Act: -0.1700
Data Index: 8644361 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.0818. Min Act: -0.1700
Data Index: 270536 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4881. Min Range: -7.4881
Max Act: 7.0193. Min Act: -0.1700
Data Index: 2758525 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.9881. Min Act: -0.1700
Data Index: 485868 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.9568. Min Act: -0.1700
Data Index: 2413117 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.9256. Min Act: -0.1700
Data Index: 3722889 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 6578378 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 5885374 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 3360679 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 8072571 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 1894741 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8943. Min Act: -0.1700
Data Index: 4658267 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8631. Min Act: -0.1700
Data Index: 6527148 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8631. Min Act: -0.1700
Data Index: 701134 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8318. Min Act: -0.1700
Data Index: 2231326 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4881. Min Range: -7.4881
Max Act: 6.8006. Min Act: -0.1700
Data Index: 1640682 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19