Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.3953. Min Act: -0.1700
Data Index: 1130566 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.3626. Min Act: -0.1700
Data Index: 6775411 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.3462. Min Act: -0.1700
Data Index: 4533049 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.2969. Min Act: -0.1700
Data Index: 3088696 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.2805. Min Act: -0.1700
Data Index: 5352503 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.2475. Min Act: -0.1700
Data Index: 2281916 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.2475. Min Act: -0.1700
Data Index: 8266257 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1978. Min Act: -0.1700
Data Index: 3909429 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1978. Min Act: -0.1700
Data Index: 4533050 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.2144. Min Act: -0.1700
Data Index: 6705522 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1812. Min Act: -0.1700
Data Index: 6775412 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1645. Min Act: -0.1700
Data Index: 2449087 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1479. Min Act: -0.1700
Data Index: 3088695 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1562. Min Act: -0.1700
Data Index: 1665668 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1312. Min Act: -0.1700
Data Index: 1791630 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1145. Min Act: -0.1700
Data Index: 6376622 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1479. Min Act: -0.1700
Data Index: 3534320 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1395. Min Act: -0.1700
Data Index: 371268 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1479. Min Act: -0.1700
Data Index: 2140768 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3953. Min Range: -2.3953
Max Act: 2.1479. Min Act: -0.1700
Data Index: 3816698 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19