Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 2549439 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.2297. Min Act: -0.1700
Data Index: 1482616 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.2297. Min Act: -0.1700
Data Index: 5419154 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 8016120 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 3614031 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 7912982 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 6382541 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 5419155 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 8357524 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3507110 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1436931 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 724809 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 279396 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3077550 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 3431355 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1699
Data Index: 4621022 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1742459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 4243729 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3424722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 4430992 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19