Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 3843133 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.4302. Min Act: -0.1700
Data Index: 5478660 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3677. Min Act: -0.1700
Data Index: 5784014 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3364. Min Act: -0.1700
Data Index: 5535192 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3052. Min Act: -0.1700
Data Index: 578153 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3052. Min Act: -0.1700
Data Index: 3554849 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3052. Min Act: -0.1700
Data Index: 5245655 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.3052. Min Act: -0.1700
Data Index: 5912269 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2739. Min Act: -0.1700
Data Index: 7252146 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2739. Min Act: -0.1700
Data Index: 1708262 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 1636444 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 3693076 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 7279037 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 203145 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2114. Min Act: -0.1700
Data Index: 6026069 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 758799 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 510317 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2114. Min Act: -0.1700
Data Index: 2647093 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.2427. Min Act: -0.1700
Data Index: 7998252 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5239. Min Range: -5.5239
Max Act: 5.1489. Min Act: -0.1700
Data Index: 3669111 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19