Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1042 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0179. Min Range: -5.0179
Max Act: 5.0179. Min Act: -0.1700
Data Index: 5191488 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0179. Min Range: -5.0179
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2177271 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0179. Min Range: -5.0179
Max Act: 5.0179. Min Act: -0.1700
Data Index: 5429035 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9866. Min Act: -0.1700
Data Index: 362436 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 5180080 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1969710 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 2309131 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 287512 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 8028295 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9241. Min Act: -0.1700
Data Index: 2934328 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 3899542 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1941373 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5012983 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1748037 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.8929. Min Act: -0.1700
Data Index: 8294519 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9241. Min Act: -0.1700
Data Index: 7154557 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9554. Min Act: -0.1700
Data Index: 3741528 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1528678 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.8929. Min Act: -0.1700
Data Index: 6962599 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0179. Min Range: -5.0179
Max Act: 4.8929. Min Act: -0.1700
Data Index: 1323366 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19