Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.6873. Min Act: -0.1700
Data Index: 5529720 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.4373. Min Act: -0.1700
Data Index: 4256005 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.4373. Min Act: -0.1700
Data Index: 6695401 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.4061. Min Act: -0.1700
Data Index: 5811816 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.4061. Min Act: -0.1700
Data Index: 2578710 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3748. Min Act: -0.1700
Data Index: 1942580 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3436. Min Act: -0.1700
Data Index: 6201346 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3436. Min Act: -0.1700
Data Index: 4742297 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4056405 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3436. Min Act: -0.1700
Data Index: 7935965 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.3123. Min Act: -0.1700
Data Index: 480076 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2811. Min Act: -0.1700
Data Index: 2540126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2498. Min Act: -0.1700
Data Index: 8672771 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2498. Min Act: -0.1700
Data Index: 445845 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2498. Min Act: -0.1700
Data Index: 728623 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2498. Min Act: -0.1700
Data Index: 4754756 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.1873. Min Act: -0.1700
Data Index: 5561832 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2186. Min Act: -0.1700
Data Index: 186845 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.2186. Min Act: -0.1700
Data Index: 6900139 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6873. Min Range: -4.6873
Max Act: 4.1873. Min Act: -0.1700
Data Index: 3721394 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19