Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.5340. Min Act: -0.1700
Data Index: 2300136 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.3146. Min Act: -0.1700
Data Index: 8154690 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2832. Min Act: -0.1700
Data Index: 4417891 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2989. Min Act: -0.1700
Data Index: 447217 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2675. Min Act: -0.1700
Data Index: 7038569 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2361. Min Act: -0.1700
Data Index: 2893038 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2361. Min Act: -0.1700
Data Index: 2054220 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.2046. Min Act: -0.1700
Data Index: 2966287 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1889. Min Act: -0.1700
Data Index: 7627856 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1889. Min Act: -0.1700
Data Index: 2627696 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1732. Min Act: -0.1700
Data Index: 5027651 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1574. Min Act: -0.1700
Data Index: 3116269 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1574. Min Act: -0.1700
Data Index: 3652510 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1574. Min Act: -0.1700
Data Index: 2180068 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1417. Min Act: -0.1700
Data Index: 661602 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4441068 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1259. Min Act: -0.1700
Data Index: 404013 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1102. Min Act: -0.1700
Data Index: 4638377 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1259. Min Act: -0.1700
Data Index: 1730845 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5340. Min Range: -3.5340
Max Act: 3.1259. Min Act: -0.1700
Data Index: 5235972 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19