Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.4041. Min Act: -0.1700
Data Index: 4618937 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2942. Min Act: -0.1700
Data Index: 2704080 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2785. Min Act: -0.1700
Data Index: 393617 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2785. Min Act: -0.1700
Data Index: 6548876 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2314. Min Act: -0.1700
Data Index: 1820129 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2314. Min Act: -0.1700
Data Index: 5005025 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2314. Min Act: -0.1700
Data Index: 5403783 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2000. Min Act: -0.1700
Data Index: 7485449 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2157. Min Act: -0.1700
Data Index: 3984761 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1842. Min Act: -0.1700
Data Index: 773183 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.2000. Min Act: -0.1700
Data Index: 8293334 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1528. Min Act: -0.1700
Data Index: 7394041 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1842. Min Act: -0.1700
Data Index: 4887223 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1528. Min Act: -0.1700
Data Index: 7940985 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1370. Min Act: -0.1700
Data Index: 3888743 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1370. Min Act: -0.1700
Data Index: 4809374 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1213. Min Act: -0.1700
Data Index: 3644458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1213. Min Act: -0.1700
Data Index: 4179382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1213. Min Act: -0.1700
Data Index: 4925565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4041. Min Range: -3.4041
Max Act: 3.1213. Min Act: -0.1700
Data Index: 5049688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19