Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.4518. Min Act: -0.1700
Data Index: 2213324 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.4206. Min Act: -0.1700
Data Index: 4648349 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3893. Min Act: -0.1700
Data Index: 4818651 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3581. Min Act: -0.1700
Data Index: 4076241 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3581. Min Act: -0.1700
Data Index: 5864122 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3581. Min Act: -0.1700
Data Index: 4108545 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3581. Min Act: -0.1700
Data Index: 4095975 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2956. Min Act: -0.1700
Data Index: 178135 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.3268. Min Act: -0.1700
Data Index: 1603453 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 8492264 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 7455142 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2956. Min Act: -0.1700
Data Index: 5040801 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 3758819 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 5881895 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 4906482 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2331. Min Act: -0.1700
Data Index: 3935381 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1323792 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1538910 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 7059031 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4518. Min Range: -5.4518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1796128 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19