Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5332 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.9076. Min Act: -0.1700
Data Index: 3163625 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.8764. Min Act: -0.1700
Data Index: 1003595 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.8451. Min Act: -0.1700
Data Index: 4299513 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.8451. Min Act: -0.1700
Data Index: 4634250 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7826. Min Act: -0.1700
Data Index: 2637811 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7514. Min Act: -0.1700
Data Index: 7535443 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7514. Min Act: -0.1700
Data Index: 1558058 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7514. Min Act: -0.1700
Data Index: 5433353 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7514. Min Act: -0.1700
Data Index: 1003591 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7201. Min Act: -0.1700
Data Index: 4629402 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7201. Min Act: -0.1700
Data Index: 4297204 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7201. Min Act: -0.1700
Data Index: 3163629 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.7201. Min Act: -0.1700
Data Index: 4634251 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6889. Min Act: -0.1700
Data Index: 4634240 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6889. Min Act: -0.1700
Data Index: 5951747 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6889. Min Act: -0.1700
Data Index: 7497250 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6264. Min Act: -0.1700
Data Index: 4850882 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6264. Min Act: -0.1700
Data Index: 4634239 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6264. Min Act: -0.1700
Data Index: 5417745 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9076. Min Range: -4.9076
Max Act: 4.6264. Min Act: -0.1700
Data Index: 2087647 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19