Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.9841. Min Act: -0.1700
Data Index: 3819537 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.8903. Min Act: -0.1700
Data Index: 4406534 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8119191 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.4216. Min Act: -0.1700
Data Index: 4166734 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3436963 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.3278. Min Act: -0.1700
Data Index: 4902077 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2966. Min Act: -0.1700
Data Index: 4913713 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.3278. Min Act: -0.1700
Data Index: 7666902 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2966. Min Act: -0.1700
Data Index: 6596238 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2966. Min Act: -0.1700
Data Index: 941957 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2653. Min Act: -0.1700
Data Index: 6903883 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2635657 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2653. Min Act: -0.1700
Data Index: 6483266 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2653. Min Act: -0.1700
Data Index: 3665384 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2653. Min Act: -0.1700
Data Index: 1500443 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 1139112 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 3680109 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 4226769 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2028. Min Act: -0.1700
Data Index: 232755 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9841. Min Range: -5.9841
Max Act: 5.2028. Min Act: -0.1700
Data Index: 7505867 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19