Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.7359. Min Act: -0.1700
Data Index: 6565248 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.7046. Min Act: -0.1700
Data Index: 3749728 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.6108. Min Act: -0.1700
Data Index: 4964932 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.5951. Min Act: -0.1700
Data Index: 4481926 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.4855. Min Act: -0.1700
Data Index: 6205115 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.4855. Min Act: -0.1700
Data Index: 7422026 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.4542. Min Act: -0.1700
Data Index: 1654488 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.4385. Min Act: -0.1700
Data Index: 584228 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.4385. Min Act: -0.1700
Data Index: 5688237 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3915. Min Act: -0.1700
Data Index: 3925068 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3758. Min Act: -0.1700
Data Index: 8474188 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3601. Min Act: -0.1700
Data Index: 1693487 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3444. Min Act: -0.1700
Data Index: 6244268 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3444. Min Act: -0.1700
Data Index: 1199769 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3444. Min Act: -0.1700
Data Index: 3181074 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3287. Min Act: -0.1700
Data Index: 10692 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.2973. Min Act: -0.1700
Data Index: 4964931 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3130. Min Act: -0.1700
Data Index: 7149261 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3130. Min Act: -0.1700
Data Index: 5843247 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7359. Min Range: -3.7359
Max Act: 3.3130. Min Act: -0.1700
Data Index: 2255263 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19