Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.6922. Min Act: -0.1700
Data Index: 1081254 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4734. Min Act: -0.1700
Data Index: 7469268 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4734. Min Act: -0.1700
Data Index: 8227168 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4422. Min Act: -0.1700
Data Index: 6133511 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4422. Min Act: -0.1700
Data Index: 2776118 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4109. Min Act: -0.1700
Data Index: 4096746 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4109. Min Act: -0.1700
Data Index: 6355438 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.3797. Min Act: -0.1700
Data Index: 1294832 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4109. Min Act: -0.1700
Data Index: 4195181 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.4109. Min Act: -0.1700
Data Index: 2804494 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.3484. Min Act: -0.1700
Data Index: 399932 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.3172. Min Act: -0.1700
Data Index: 6092422 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.3172. Min Act: -0.1700
Data Index: 1399413 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2859. Min Act: -0.1700
Data Index: 4386403 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2547. Min Act: -0.1700
Data Index: 3215140 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2859. Min Act: -0.1700
Data Index: 1761336 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2234. Min Act: -0.1700
Data Index: 8133293 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.1922. Min Act: -0.1700
Data Index: 3075187 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2234. Min Act: -0.1700
Data Index: 4118258 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6922. Min Range: -6.6922
Max Act: 6.2547. Min Act: -0.1700
Data Index: 2804490 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19