Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.4205. Min Act: -0.1700
Data Index: 5686124 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.3421. Min Act: -0.1700
Data Index: 3004849 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.3107. Min Act: -0.1700
Data Index: 5104720 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2950. Min Act: -0.1700
Data Index: 1393475 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.3107. Min Act: -0.1700
Data Index: 5216099 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.3107. Min Act: -0.1700
Data Index: 3899310 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2793. Min Act: -0.1700
Data Index: 5742081 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.3107. Min Act: -0.1700
Data Index: 4927669 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2793. Min Act: -0.1700
Data Index: 665549 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2793. Min Act: -0.1700
Data Index: 6514398 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2950. Min Act: -0.1700
Data Index: 3308751 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2950. Min Act: -0.1700
Data Index: 8601908 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2636. Min Act: -0.1700
Data Index: 7173246 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2636. Min Act: -0.1700
Data Index: 4291335 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2636. Min Act: -0.1700
Data Index: 8508606 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2479. Min Act: -0.1700
Data Index: 4668533 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2322. Min Act: -0.1700
Data Index: 5078287 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2793. Min Act: -0.1700
Data Index: 6697756 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2322. Min Act: -0.1700
Data Index: 8006071 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4205. Min Range: -3.4205
Max Act: 3.2479. Min Act: -0.1700
Data Index: 5008655 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19