Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.9552. Min Act: -0.1700
Data Index: 6873188 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.9552. Min Act: -0.1700
Data Index: 5894020 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.9552. Min Act: -0.1700
Data Index: 7781042 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.9552. Min Act: -0.1700
Data Index: 3513510 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.9552. Min Act: -0.1700
Data Index: 3021166 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8927. Min Act: -0.1700
Data Index: 7019142 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 3822713 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 3875656 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 7865170 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 8481747 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 2699610 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 995167 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 2496764 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 4715646 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8614. Min Act: -0.1700
Data Index: 5368521 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8301. Min Act: -0.1700
Data Index: 1176533 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8301. Min Act: -0.1700
Data Index: 676683 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8301. Min Act: -0.1700
Data Index: 6152936 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8301. Min Act: -0.1700
Data Index: 4532415 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9552. Min Range: -3.9552
Max Act: 3.8301. Min Act: -0.1700
Data Index: 2488220 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19