Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.7190. Min Act: -0.1700
Data Index: 1991073 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.7190. Min Act: -0.1700
Data Index: 7354650 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.7190. Min Act: -0.1700
Data Index: 1835310 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6877. Min Act: -0.1700
Data Index: 4462172 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6877. Min Act: -0.1700
Data Index: 1835308 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6252. Min Act: -0.1700
Data Index: 6573649 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6252. Min Act: -0.1697
Data Index: 1207128 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6252. Min Act: -0.1700
Data Index: 169792 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.6252. Min Act: -0.1700
Data Index: 1014231 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5940. Min Act: -0.1700
Data Index: 4096089 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5940. Min Act: -0.1700
Data Index: 6035105 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5940. Min Act: -0.1700
Data Index: 5466816 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 2369460 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 5848298 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 1924711 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 4112378 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 772790 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 5988460 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1700
Data Index: 4280241 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7190. Min Range: -4.7190
Max Act: 4.5627. Min Act: -0.1699
Data Index: 4284043 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19