Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.2444. Min Act: -0.1700
Data Index: 403306 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.2444. Min Act: -0.1700
Data Index: 4943625 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.1193. Min Act: -0.1700
Data Index: 2347086 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.1193. Min Act: -0.1700
Data Index: 8698716 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.1193. Min Act: -0.1700
Data Index: 4904281 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.1193. Min Act: -0.1700
Data Index: 2076480 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.0881. Min Act: -0.1700
Data Index: 5303477 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.0568. Min Act: -0.1700
Data Index: 2664991 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.0256. Min Act: -0.1700
Data Index: 4146827 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5421685 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2444. Min Range: -4.2444
Max Act: 4.0256. Min Act: -0.1700
Data Index: 8532198 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9943. Min Act: -0.1700
Data Index: 6258746 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 4544175 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9943. Min Act: -0.1700
Data Index: 4561526 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5538051 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 7564566 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 4307179 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 6461150 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 5118496 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2444. Min Range: -4.2444
Max Act: 3.9631. Min Act: -0.1700
Data Index: 2830106 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19