Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.6297. Min Act: -0.1700
Data Index: 5015137 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.6297. Min Act: -0.1700
Data Index: 3306963 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.4110. Min Act: -0.1700
Data Index: 1577556 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.4110. Min Act: -0.1700
Data Index: 6146653 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.3485. Min Act: -0.1700
Data Index: 5132340 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.3172. Min Act: -0.1700
Data Index: 1111385 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.3172. Min Act: -0.1700
Data Index: 3903534 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.3172. Min Act: -0.1700
Data Index: 4694053 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3868621 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3103647 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.2860. Min Act: -0.1700
Data Index: 1616941 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.2547. Min Act: -0.1700
Data Index: 450137 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.2235. Min Act: -0.1700
Data Index: 6106209 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1922. Min Act: -0.1700
Data Index: 3903535 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1922. Min Act: -0.1700
Data Index: 5948086 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1922. Min Act: -0.1700
Data Index: 362831 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1922. Min Act: -0.1700
Data Index: 4461105 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1610. Min Act: -0.1700
Data Index: 3029738 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1610. Min Act: -0.1700
Data Index: 420270 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6297. Min Range: -6.6297
Max Act: 6.1610. Min Act: -0.1700
Data Index: 4931636 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19