Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5947. Min Act: -0.1700
Data Index: 405919 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5009. Min Act: -0.1700
Data Index: 4059056 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5322. Min Act: -0.1700
Data Index: 1109101 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4697. Min Act: -0.1700
Data Index: 4390320 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 6612296 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 1882094 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3759. Min Act: -0.1700
Data Index: 5067083 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3447. Min Act: -0.1700
Data Index: 2324840 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3447. Min Act: -0.1700
Data Index: 7321029 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3759. Min Act: -0.1700
Data Index: 5031396 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 4960763 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 2324838 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 8082108 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2509. Min Act: -0.1700
Data Index: 357596 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2197. Min Act: -0.1700
Data Index: 24321 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2509. Min Act: -0.1700
Data Index: 8774977 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.1884. Min Act: -0.1700
Data Index: 811447 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.1884. Min Act: -0.1700
Data Index: 1994466 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2197. Min Act: -0.1700
Data Index: 4713600 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.1884. Min Act: -0.1700
Data Index: 4619645 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19