Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4854 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.9240. Min Act: -0.1700
Data Index: 2953400 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.7677. Min Act: -0.1700
Data Index: 1293990 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.7365. Min Act: -0.1700
Data Index: 3037584 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3651304 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3174982 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6740. Min Act: -0.1700
Data Index: 4129642 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6740. Min Act: -0.1700
Data Index: 7424659 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6115. Min Act: -0.1700
Data Index: 8527561 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6427. Min Act: -0.1700
Data Index: 2647960 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6115. Min Act: -0.1700
Data Index: 947006 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.6115. Min Act: -0.1700
Data Index: 5049360 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5802. Min Act: -0.1700
Data Index: 2901628 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5802. Min Act: -0.1700
Data Index: 8370330 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5802. Min Act: -0.1700
Data Index: 1547461 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5490. Min Act: -0.1700
Data Index: 3539117 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5177. Min Act: -0.1700
Data Index: 1338323 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5177. Min Act: -0.1700
Data Index: 2698524 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5177. Min Act: -0.1700
Data Index: 1467726 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.5177. Min Act: -0.1700
Data Index: 3469327 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9240. Min Range: -5.9240
Max Act: 5.4865. Min Act: -0.1700
Data Index: 68125 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19