Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5383. Min Act: -0.1700
Data Index: 6380787 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5383. Min Act: -0.1570
Data Index: 7382564 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5383. Min Act: -0.1700
Data Index: 5135128 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5383. Min Act: -0.1700
Data Index: 3046104 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5295. Min Act: -0.1700
Data Index: 417199 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5032. Min Act: -0.1700
Data Index: 1527729 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4944. Min Act: -0.1700
Data Index: 1649520 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5032. Min Act: -0.1699
Data Index: 2604107 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5120. Min Act: -0.1686
Data Index: 1015112 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.5120. Min Act: -0.1697
Data Index: 1806227 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4944. Min Act: -0.1700
Data Index: 4625527 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4944. Min Act: -0.1700
Data Index: 4648955 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4944. Min Act: -0.1698
Data Index: 4373077 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4769. Min Act: -0.1694
Data Index: 7253794 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4856. Min Act: -0.1700
Data Index: 6114261 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4681. Min Act: -0.1694
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4681. Min Act: -0.1677
Data Index: 7913691 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4681. Min Act: -0.1700
Data Index: 2729962 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4769. Min Act: -0.1700
Data Index: 6206752 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5383. Min Range: -1.5383
Max Act: 1.4593. Min Act: -0.1699
Data Index: 2057815 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19