Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.5277. Min Act: -0.1700
Data Index: 4297646 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.4027. Min Act: -0.1700
Data Index: 1883538 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3089. Min Act: -0.1700
Data Index: 1702219 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.4339. Min Act: -0.1700
Data Index: 4284579 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3714. Min Act: -0.1700
Data Index: 2177038 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2777. Min Act: -0.1700
Data Index: 5630777 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2777. Min Act: -0.1700
Data Index: 1204208 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3714. Min Act: -0.1700
Data Index: 4842781 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3402. Min Act: -0.1700
Data Index: 4264778 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3089. Min Act: -0.1700
Data Index: 5036885 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2777. Min Act: -0.1700
Data Index: 2562549 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2777. Min Act: -0.1700
Data Index: 8209934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3402. Min Act: -0.1700
Data Index: 3120303 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2464. Min Act: -0.1700
Data Index: 5637528 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2464. Min Act: -0.1700
Data Index: 6241778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2464. Min Act: -0.1700
Data Index: 4506051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2464. Min Act: -0.1700
Data Index: 4670746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2464. Min Act: -0.1700
Data Index: 8342796 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2152. Min Act: -0.1700
Data Index: 1267689 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1839. Min Act: -0.1700
Data Index: 543684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19