Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.4422. Min Act: -0.1700
Data Index: 7046718 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.4110. Min Act: -0.1700
Data Index: 185143 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.3485. Min Act: -0.1700
Data Index: 2820647 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 8234255 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 4275737 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 4896783 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2547. Min Act: -0.1679
Data Index: 184882 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2235. Min Act: -0.1516
Data Index: 2753414 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.2235. Min Act: -0.1700
Data Index: 5948170 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1922. Min Act: -0.1700
Data Index: 267629 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1922. Min Act: -0.1700
Data Index: 8491106 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1922. Min Act: -0.1700
Data Index: 5113239 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1610. Min Act: -0.1700
Data Index: 3391702 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1610. Min Act: -0.1700
Data Index: 8063401 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1297. Min Act: -0.1700
Data Index: 3798940 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1297. Min Act: -0.1700
Data Index: 824139 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1297. Min Act: -0.1700
Data Index: 4785630 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1297. Min Act: -0.1700
Data Index: 2335051 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.1297. Min Act: -0.1700
Data Index: 7751119 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4422. Min Range: -4.4422
Max Act: 4.0985. Min Act: -0.1700
Data Index: 6593829 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19