Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.6114. Min Act: -0.1700
Data Index: 970312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5801. Min Act: -0.1700
Data Index: 2075488 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 2932816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 959583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 3074395 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 4465820 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 4204985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 1927149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 8365532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 4200355 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 2678452 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 3575431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 3104844 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1699
Data Index: 2677418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 8703749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 3104307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5488. Min Act: -0.1700
Data Index: 8465745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5175. Min Act: -0.1699
Data Index: 3884397 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5175. Min Act: -0.1700
Data Index: 89111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6114. Min Range: -3.6114
Max Act: 3.5175. Min Act: -0.1700
Data Index: 4535725 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19