Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 193 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7703. Min Act: -0.1700
Data Index: 13523 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7617. Min Act: -0.1700
Data Index: 8250868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7617. Min Act: -0.1700
Data Index: 3164887 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7444. Min Act: -0.1700
Data Index: 6154141 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7530. Min Act: -0.1700
Data Index: 7504443 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7358. Min Act: -0.1700
Data Index: 5067437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7358. Min Act: -0.1700
Data Index: 3051276 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7098. Min Act: -0.1699
Data Index: 144210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7098. Min Act: -0.1699
Data Index: 2206286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7011. Min Act: -0.1693
Data Index: 1471050 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7011. Min Act: -0.1699
Data Index: 2180494 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6925. Min Act: -0.1700
Data Index: 3926519 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6838. Min Act: -0.1658
Data Index: 1023135 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6838. Min Act: -0.1700
Data Index: 6404768 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6925. Min Act: -0.1700
Data Index: 7431091 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6838. Min Act: -0.1700
Data Index: 8267206 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6838. Min Act: -0.1700
Data Index: 6577134 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6751. Min Act: -0.1700
Data Index: 7654800 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6838. Min Act: -0.1700
Data Index: 8009006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.6664. Min Act: -0.1696
Data Index: 4180826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19