Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3854 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.5499. Min Act: -0.1700
Data Index: 1399126 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.5187. Min Act: -0.1700
Data Index: 4297857 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.4562. Min Act: -0.1700
Data Index: 6461739 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3937. Min Act: -0.1700
Data Index: 5835927 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3937. Min Act: -0.1700
Data Index: 5027035 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3624. Min Act: -0.1700
Data Index: 3741544 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3624. Min Act: -0.1700
Data Index: 977800 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3312. Min Act: -0.1700
Data Index: 6448807 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3312. Min Act: -0.1700
Data Index: 5296642 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3312. Min Act: -0.1700
Data Index: 3094823 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2999. Min Act: -0.1700
Data Index: 1337566 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3312. Min Act: -0.1700
Data Index: 2427214 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.3312. Min Act: -0.1700
Data Index: 5027036 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2999. Min Act: -0.1700
Data Index: 3438021 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2999. Min Act: -0.1700
Data Index: 3323090 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2999. Min Act: -0.1700
Data Index: 1337565 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2999. Min Act: -0.1700
Data Index: 4872803 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2374. Min Act: -0.1700
Data Index: 1082131 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2687. Min Act: -0.1700
Data Index: 2853955 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5499. Min Range: -4.5499
Max Act: 4.2687. Min Act: -0.1700
Data Index: 154953 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19