Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5053 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.5216. Min Act: -0.1700
Data Index: 6730915 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.3341. Min Act: -0.1700
Data Index: 5851874 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.3028. Min Act: -0.1700
Data Index: 8177070 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.2716. Min Act: -0.1700
Data Index: 7672206 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.2716. Min Act: -0.1700
Data Index: 1218365 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.2403. Min Act: -0.1700
Data Index: 7077915 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.2091. Min Act: -0.1700
Data Index: 7826943 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1778. Min Act: -0.1700
Data Index: 2189392 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1778. Min Act: -0.1700
Data Index: 6461029 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1466. Min Act: -0.1700
Data Index: 5170242 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1153. Min Act: -0.1700
Data Index: 6608661 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1153. Min Act: -0.1700
Data Index: 1469734 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1153. Min Act: -0.1700
Data Index: 3688488 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.1153. Min Act: -0.1700
Data Index: 7013495 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0841. Min Act: -0.1700
Data Index: 3252295 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0528. Min Act: -0.1700
Data Index: 6057720 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0841. Min Act: -0.1700
Data Index: 6027101 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0841. Min Act: -0.1700
Data Index: 890169 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0841. Min Act: -0.1700
Data Index: 1608390 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5216. Min Range: -5.5216
Max Act: 5.0528. Min Act: -0.1700
Data Index: 4189866 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19