Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.6340. Min Act: -0.1700
Data Index: 3945408 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.5557. Min Act: -0.1700
Data Index: 8184977 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.4774. Min Act: -0.1700
Data Index: 3379938 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3991. Min Act: -0.1700
Data Index: 5148439 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.4304. Min Act: -0.1700
Data Index: 1166513 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3834. Min Act: -0.1700
Data Index: 5893369 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3677. Min Act: -0.1700
Data Index: 176065 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3834. Min Act: -0.1700
Data Index: 4468302 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3520. Min Act: -0.1700
Data Index: 7451788 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3834. Min Act: -0.1700
Data Index: 6333081 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3363. Min Act: -0.1700
Data Index: 7978806 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3363. Min Act: -0.1700
Data Index: 3980726 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.2892. Min Act: -0.1700
Data Index: 2476105 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3206. Min Act: -0.1700
Data Index: 3093762 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3206. Min Act: -0.1700
Data Index: 27734 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3206. Min Act: -0.1700
Data Index: 2809968 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3206. Min Act: -0.1700
Data Index: 1887930 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.2892. Min Act: -0.1700
Data Index: 3707188 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3049. Min Act: -0.1700
Data Index: 4208993 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6340. Min Range: -3.6340
Max Act: 3.3049. Min Act: -0.1700
Data Index: 5035757 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19