Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.4449. Min Act: -0.1700
Data Index: 8289901 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3352. Min Act: -0.1700
Data Index: 4287877 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3195. Min Act: -0.1700
Data Index: 8520466 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3195. Min Act: -0.1700
Data Index: 3331473 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3038. Min Act: -0.1700
Data Index: 1329781 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3038. Min Act: -0.1700
Data Index: 7609177 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.3038. Min Act: -0.1700
Data Index: 4766566 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2881. Min Act: -0.1700
Data Index: 5493958 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2881. Min Act: -0.1700
Data Index: 2545975 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2881. Min Act: -0.1700
Data Index: 2526635 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2881. Min Act: -0.1700
Data Index: 5409380 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 2979996 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 5776521 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 2137467 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 5708625 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 6649386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 4091682 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2567. Min Act: -0.1700
Data Index: 7486304 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2567. Min Act: -0.1700
Data Index: 7468248 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2724. Min Act: -0.1700
Data Index: 7323087 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19