Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.7313. Min Act: -0.1700
Data Index: 7436175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.6673. Min Act: -0.1700
Data Index: 2266421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.6673. Min Act: -0.1700
Data Index: 8449936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5869. Min Act: -0.1700
Data Index: 5081339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5708. Min Act: -0.1700
Data Index: 6739570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5869. Min Act: -0.1700
Data Index: 2330588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5547. Min Act: -0.1700
Data Index: 3829407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5547. Min Act: -0.1700
Data Index: 1167732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.5062. Min Act: -0.1700
Data Index: 8513610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4900. Min Act: -0.1700
Data Index: 5928967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4900. Min Act: -0.1700
Data Index: 3007000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4900. Min Act: -0.1700
Data Index: 8066110 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4738. Min Act: -0.1700
Data Index: 4386273 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4738. Min Act: -0.1700
Data Index: 5807158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4575. Min Act: -0.1700
Data Index: 5649318 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4738. Min Act: -0.1700
Data Index: 4248932 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4738. Min Act: -0.1700
Data Index: 2368410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4900. Min Act: -0.1700
Data Index: 3880649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4575. Min Act: -0.1700
Data Index: 3430704 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7313. Min Range: -2.7313
Max Act: 2.4575. Min Act: -0.1700
Data Index: 5051102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19