Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0573. Min Range: -6.0573
Max Act: 6.0573. Min Act: -0.1700
Data Index: 8757282 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6716409 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.9323. Min Act: -0.1700
Data Index: 7016675 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3887683 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.9010. Min Act: -0.1700
Data Index: 5930034 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.9010. Min Act: -0.1700
Data Index: 789675 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8698. Min Act: -0.1700
Data Index: 5434960 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8698. Min Act: -0.1700
Data Index: 7266385 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8385. Min Act: -0.1700
Data Index: 7818269 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8698. Min Act: -0.1700
Data Index: 6089000 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8385. Min Act: -0.1700
Data Index: 6522472 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.8073. Min Act: -0.1700
Data Index: 789149 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 7279159 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 4274351 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7448. Min Act: -0.1700
Data Index: 242156 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 2929890 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 3674385 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 2279677 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7760. Min Act: -0.1700
Data Index: 6984628 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0573. Min Range: -6.0573
Max Act: 5.7135. Min Act: -0.1700
Data Index: 2958390 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19