Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5565. Min Range: -4.5565
Max Act: 4.5565. Min Act: -0.1700
Data Index: 5839134 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5565. Min Range: -4.5565
Max Act: 4.0877. Min Act: -0.1700
Data Index: 4470828 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5565. Min Range: -4.5565
Max Act: 4.0564. Min Act: -0.1700
Data Index: 5508819 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5565. Min Range: -4.5565
Max Act: 4.0252. Min Act: -0.1700
Data Index: 3066534 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9626. Min Act: -0.1700
Data Index: 1327171 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9314. Min Act: -0.1700
Data Index: 6903690 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9314. Min Act: -0.1700
Data Index: 4225356 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9314. Min Act: -0.1700
Data Index: 4127086 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9001. Min Act: -0.1700
Data Index: 440105 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8689. Min Act: -0.1700
Data Index: 5285162 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.9001. Min Act: -0.1700
Data Index: 3689278 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 5613182 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 7369438 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 3839554 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 5417253 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 2465522 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4225357 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 1805753 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4550625 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5565. Min Range: -4.5565
Max Act: 3.7750. Min Act: -0.1700
Data Index: 3592644 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19