Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2176 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.8237. Min Act: -0.1700
Data Index: 2267122 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.6049. Min Act: -0.1700
Data Index: 8054876 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.6049. Min Act: -0.1700
Data Index: 4315534 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.6049. Min Act: -0.1700
Data Index: 4356921 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.5424. Min Act: -0.1700
Data Index: 6150328 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.5424. Min Act: -0.1700
Data Index: 5066162 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4799. Min Act: -0.1700
Data Index: 125250 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4799. Min Act: -0.1700
Data Index: 5436552 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4799. Min Act: -0.1700
Data Index: 2088656 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4487. Min Act: -0.1700
Data Index: 1888901 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4174. Min Act: -0.1700
Data Index: 2292650 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.4174. Min Act: -0.1700
Data Index: 3364367 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3862. Min Act: -0.1700
Data Index: 838441 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3862. Min Act: -0.1700
Data Index: 7142840 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3549. Min Act: -0.1700
Data Index: 8156351 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3862. Min Act: -0.1700
Data Index: 5499287 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3549. Min Act: -0.1700
Data Index: 2906542 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3237. Min Act: -0.1700
Data Index: 1731182 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3237. Min Act: -0.1700
Data Index: 1137140 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8237. Min Range: -7.8237
Max Act: 7.3237. Min Act: -0.1700
Data Index: 3719199 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19