Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1700. Min Act: -0.1700
Data Index: 2463879 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1700. Min Act: -0.1700
Data Index: 5427984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1700. Min Act: -0.1700
Data Index: 5641107 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1700. Min Act: -0.1700
Data Index: 6019581 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 8774401 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 371212 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 72434 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 669724 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 1347582 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 8280309 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 8148060 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 547082 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 8045336 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.1199. Min Act: -0.1700
Data Index: 3027997 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 921520 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 235453 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 776384 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 117225 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 363200 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1700. Min Range: -2.1700
Max Act: 2.0864. Min Act: -0.1700
Data Index: 964293 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19