Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.5615. Min Act: -0.1700
Data Index: 5275431 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.4990. Min Act: -0.1700
Data Index: 2172770 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.3740. Min Act: -0.1700
Data Index: 6866208 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.1240. Min Act: -0.1700
Data Index: 8738848 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0615. Min Act: -0.1699
Data Index: 8221588 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0615. Min Act: -0.1700
Data Index: 1346778 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.9990. Min Act: -0.1700
Data Index: 8258234 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.9990. Min Act: -0.1700
Data Index: 5286873 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.9365. Min Act: -0.1700
Data Index: 5275430 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4408091 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8740. Min Act: -0.1700
Data Index: 2034206 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8740. Min Act: -0.1700
Data Index: 7867383 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.9365. Min Act: -0.1700
Data Index: 1149314 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4468232 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8740. Min Act: -0.1700
Data Index: 1439269 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8115. Min Act: -0.1700
Data Index: 4314707 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8115. Min Act: -0.1700
Data Index: 8240175 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.8115. Min Act: -0.1700
Data Index: 1566018 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.7490. Min Act: -0.1700
Data Index: 94388 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5615. Min Range: -7.5615
Max Act: 6.7490. Min Act: -0.1700
Data Index: 5485368 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19