Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.4848. Min Act: -0.1700
Data Index: 584955 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.5160. Min Act: -0.1700
Data Index: 4027867 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7687470 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.4223. Min Act: -0.1700
Data Index: 33248 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.4223. Min Act: -0.1700
Data Index: 8646434 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3598. Min Act: -0.1700
Data Index: 6883379 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3598. Min Act: -0.1700
Data Index: 8487824 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5618338 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7927965 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5102682 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7440289 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3285. Min Act: -0.1700
Data Index: 4283696 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2973. Min Act: -0.1700
Data Index: 605172 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.3285. Min Act: -0.1700
Data Index: 1568707 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2660. Min Act: -0.1700
Data Index: 7854594 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2973. Min Act: -0.1700
Data Index: 4027865 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2973. Min Act: -0.1700
Data Index: 6746475 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2973. Min Act: -0.1700
Data Index: 5400032 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2973. Min Act: -0.1700
Data Index: 6906466 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5160. Min Range: -5.5160
Max Act: 5.2348. Min Act: -0.1700
Data Index: 1236100 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19