Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2262647 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.4017. Min Act: -0.1700
Data Index: 8676419 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3705. Min Act: -0.1700
Data Index: 362778 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3705. Min Act: -0.1700
Data Index: 1576566 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3705. Min Act: -0.1700
Data Index: 6527675 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3392. Min Act: -0.1700
Data Index: 6858077 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3705. Min Act: -0.1700
Data Index: 8044505 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3392. Min Act: -0.1700
Data Index: 7285105 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3080. Min Act: -0.1700
Data Index: 1660563 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3080. Min Act: -0.1700
Data Index: 700698 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3080. Min Act: -0.1700
Data Index: 6467518 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5183531 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2455. Min Act: -0.1700
Data Index: 715856 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2767. Min Act: -0.1700
Data Index: 4019204 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1248971 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2767. Min Act: -0.1700
Data Index: 11094 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2767. Min Act: -0.1700
Data Index: 7651062 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3703532 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2767. Min Act: -0.1700
Data Index: 199168 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4330. Min Range: -6.4330
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1202686 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19