Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.2148. Min Act: -0.1700
Data Index: 1342187 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9961. Min Act: -0.1700
Data Index: 2147593 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9961. Min Act: -0.1700
Data Index: 4115556 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9648. Min Act: -0.1700
Data Index: 5664061 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9023. Min Act: -0.1700
Data Index: 8384253 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9023. Min Act: -0.1700
Data Index: 582386 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2741983 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8398. Min Act: -0.1700
Data Index: 8323929 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8398. Min Act: -0.1700
Data Index: 6758163 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8398. Min Act: -0.1700
Data Index: 38186 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8086. Min Act: -0.1700
Data Index: 1408144 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8398. Min Act: -0.1700
Data Index: 6008877 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7773. Min Act: -0.1700
Data Index: 1958873 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8086. Min Act: -0.1700
Data Index: 4754174 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.8086. Min Act: -0.1700
Data Index: 8471426 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7461. Min Act: -0.1700
Data Index: 2720398 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7461. Min Act: -0.1700
Data Index: 7196157 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7773. Min Act: -0.1700
Data Index: 4696844 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7461. Min Act: -0.1700
Data Index: 2990441 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2148. Min Range: -5.2148
Max Act: 4.7148. Min Act: -0.1700
Data Index: 1747135 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19