Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2930. Min Range: -4.2930
Max Act: 4.2930. Min Act: -0.1700
Data Index: 4011849 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.7147. Min Act: -0.1700
Data Index: 991219 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6990. Min Act: -0.1700
Data Index: 2750264 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6677. Min Act: -0.1700
Data Index: 556292 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6521. Min Act: -0.1700
Data Index: 4978430 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6365. Min Act: -0.1700
Data Index: 4495570 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6365. Min Act: -0.1700
Data Index: 960541 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2097564 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5738. Min Act: -0.1700
Data Index: 2401181 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5582. Min Act: -0.1700
Data Index: 8399371 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5425. Min Act: -0.1700
Data Index: 6602602 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5425. Min Act: -0.1700
Data Index: 7480568 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5269. Min Act: -0.1700
Data Index: 8320153 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5112. Min Act: -0.1700
Data Index: 3012064 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5112. Min Act: -0.1700
Data Index: 2074877 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.5112. Min Act: -0.1700
Data Index: 3028633 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.4799. Min Act: -0.1700
Data Index: 8303671 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.4799. Min Act: -0.1700
Data Index: 411674 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.4799. Min Act: -0.1700
Data Index: 8476437 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2930. Min Range: -4.2930
Max Act: 3.4642. Min Act: -0.1700
Data Index: 3532746 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19