Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2366 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.1968. Min Act: -0.1700
Data Index: 8100857 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.1031. Min Act: -0.1700
Data Index: 3363573 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0718. Min Act: -0.1700
Data Index: 2651396 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.1656. Min Act: -0.1700
Data Index: 3813129 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.1031. Min Act: -0.1700
Data Index: 3363569 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.1031. Min Act: -0.1700
Data Index: 3813132 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0718. Min Act: -0.1700
Data Index: 5087046 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9780. Min Act: -0.1700
Data Index: 2533820 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0093. Min Act: -0.1700
Data Index: 6348970 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0093. Min Act: -0.1700
Data Index: 5373662 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0405. Min Act: -0.1700
Data Index: 8825654 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0405. Min Act: -0.1700
Data Index: 8442365 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9468. Min Act: -0.1700
Data Index: 3699180 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9468. Min Act: -0.1700
Data Index: 6381060 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9780. Min Act: -0.1700
Data Index: 7558045 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9780. Min Act: -0.1700
Data Index: 7453712 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1968. Min Range: -4.1968
Max Act: 4.0405. Min Act: -0.1700
Data Index: 2618367 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9780. Min Act: -0.1700
Data Index: 2651398 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9468. Min Act: -0.1700
Data Index: 4309636 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1968. Min Range: -4.1968
Max Act: 3.9468. Min Act: -0.1700
Data Index: 2996777 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19