Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1589 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.2464. Min Act: -0.1272
Data Index: 7005391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1715. Min Act: -0.1146
Data Index: 6714440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1715. Min Act: -0.1146
Data Index: 4302580 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1627. Min Act: -0.1146
Data Index: 145083 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1671. Min Act: -0.1146
Data Index: 6594882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1671. Min Act: -0.1146
Data Index: 8817361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1496. Min Act: -0.1146
Data Index: 2577952 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1364. Min Act: -0.1146
Data Index: 1979456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1408. Min Act: -0.1146
Data Index: 2898384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1320. Min Act: -0.1146
Data Index: 989706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1276. Min Act: -0.1146
Data Index: 5138802 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1364. Min Act: -0.1146
Data Index: 3509115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1276. Min Act: -0.1146
Data Index: 8621093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1276. Min Act: -0.1146
Data Index: 4937557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1232. Min Act: -0.1146
Data Index: 4324576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1145. Min Act: -0.1146
Data Index: 8802773 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1276. Min Act: -0.1146
Data Index: 3387973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1232. Min Act: -0.1146
Data Index: 1361814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1276. Min Act: -0.1146
Data Index: 446903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2464. Min Range: -1.2464
Max Act: 1.1188. Min Act: -0.1146
Data Index: 8397272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19