Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4876 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3858. Min Act: -0.1700
Data Index: 2983221 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3858. Min Act: -0.1700
Data Index: 642469 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3858. Min Act: -0.1700
Data Index: 2199453 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3858. Min Act: -0.1700
Data Index: 2045945 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3233. Min Act: -0.1700
Data Index: 8152125 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3233. Min Act: -0.1700
Data Index: 7166318 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.2608. Min Act: -0.1700
Data Index: 3128260 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.3233. Min Act: -0.1700
Data Index: 7175092 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 3849833 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 4304621 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 5276518 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 71400 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 5955147 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 1604680 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 6850608 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 3633749 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 5752916 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 4175656 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 8752249 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3858. Min Range: -7.3858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 2350929 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19