Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.7457. Min Act: -0.1700
Data Index: 3770270 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.6832. Min Act: -0.1700
Data Index: 5076213 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.5582. Min Act: -0.1700
Data Index: 6956211 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.4957. Min Act: -0.1700
Data Index: 713812 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.4332. Min Act: -0.1700
Data Index: 2162650 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.4332. Min Act: -0.1700
Data Index: 625281 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.4332. Min Act: -0.1700
Data Index: 5497933 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.4332. Min Act: -0.1700
Data Index: 2225429 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.3395. Min Act: -0.1700
Data Index: 6394964 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.2770. Min Act: -0.1700
Data Index: 6735659 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.2145. Min Act: -0.1700
Data Index: 589302 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1832. Min Act: -0.1700
Data Index: 6227039 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1832. Min Act: -0.1700
Data Index: 2200744 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1832. Min Act: -0.1700
Data Index: 6915395 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1520. Min Act: -0.1700
Data Index: 6631385 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1520. Min Act: -0.1700
Data Index: 3677478 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1207. Min Act: -0.1700
Data Index: 6175663 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1207. Min Act: -0.1700
Data Index: 1773851 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1207. Min Act: -0.1700
Data Index: 6068253 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7457. Min Range: -6.7457
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7627760 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19