Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.2179. Min Act: -0.1700
Data Index: 1704544 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.1242. Min Act: -0.1700
Data Index: 2024031 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0929. Min Act: -0.1700
Data Index: 5009486 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0304. Min Act: -0.1700
Data Index: 4053479 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1787229 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0616. Min Act: -0.1700
Data Index: 6392680 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1125341 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2179. Min Range: -4.2179
Max Act: 4.0304. Min Act: -0.1700
Data Index: 3387555 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9991. Min Act: -0.1700
Data Index: 7264587 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9991. Min Act: -0.1700
Data Index: 2834858 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9991. Min Act: -0.1700
Data Index: 4021648 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9991. Min Act: -0.1700
Data Index: 3772876 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9679. Min Act: -0.1700
Data Index: 2834860 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9679. Min Act: -0.1700
Data Index: 5631159 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9366. Min Act: -0.1700
Data Index: 5791097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9679. Min Act: -0.1700
Data Index: 936506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9366. Min Act: -0.1700
Data Index: 3755442 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9366. Min Act: -0.1700
Data Index: 6025118 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9053. Min Act: -0.1700
Data Index: 6025120 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2179. Min Range: -4.2179
Max Act: 3.9679. Min Act: -0.1700
Data Index: 2242046 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19