Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.7087. Min Act: -0.1700
Data Index: 6049477 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.6767. Min Act: -0.1700
Data Index: 3466789 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.6286. Min Act: -0.1700
Data Index: 5003604 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.6125. Min Act: -0.1700
Data Index: 4659209 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.6125. Min Act: -0.1700
Data Index: 2514083 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.6286. Min Act: -0.1700
Data Index: 24540 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 2701033 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 5922020 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 5003612 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 3662265 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 3597498 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5964. Min Act: -0.1700
Data Index: 2251615 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 7056169 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 5003603 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5642. Min Act: -0.1700
Data Index: 487275 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 3943881 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 8024185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 8128874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5803. Min Act: -0.1700
Data Index: 4951157 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7087. Min Range: -2.7087
Max Act: 2.5642. Min Act: -0.1700
Data Index: 5499247 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19