Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.3123. Min Act: -0.1700
Data Index: 7846826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2966. Min Act: -0.1700
Data Index: 1152954 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2966. Min Act: -0.1700
Data Index: 4913888 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2809. Min Act: -0.1700
Data Index: 944857 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2495. Min Act: -0.1700
Data Index: 2442150 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2495. Min Act: -0.1700
Data Index: 3901993 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2180. Min Act: -0.1700
Data Index: 3431230 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1709. Min Act: -0.1700
Data Index: 2570122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.2023. Min Act: -0.1700
Data Index: 4676208 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1394. Min Act: -0.1700
Data Index: 3403361 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1394. Min Act: -0.1700
Data Index: 8702019 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1394. Min Act: -0.1700
Data Index: 1440588 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1079. Min Act: -0.1700
Data Index: 6312579 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1079. Min Act: -0.1700
Data Index: 5922655 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1236. Min Act: -0.1700
Data Index: 2566963 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.0921. Min Act: -0.1700
Data Index: 3299921 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1079. Min Act: -0.1700
Data Index: 3355258 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.1079. Min Act: -0.1700
Data Index: 587990 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.0921. Min Act: -0.1700
Data Index: 177038 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3123. Min Range: -3.3123
Max Act: 3.0921. Min Act: -0.1700
Data Index: 1366484 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19