Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4330631 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5764. Min Act: -0.1700
Data Index: 4984904 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5139. Min Act: -0.1700
Data Index: 3083390 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5452. Min Act: -0.1700
Data Index: 3800756 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5139. Min Act: -0.1700
Data Index: 3214517 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.4514. Min Act: -0.1700
Data Index: 5197191 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3577. Min Act: -0.1700
Data Index: 6175332 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3264. Min Act: -0.1700
Data Index: 3978234 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3264. Min Act: -0.1700
Data Index: 2235966 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2952. Min Act: -0.1700
Data Index: 2235969 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 6704097 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1702. Min Act: -0.1700
Data Index: 8017303 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 3440288 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1702. Min Act: -0.1700
Data Index: 1264186 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2014. Min Act: -0.1700
Data Index: 2279011 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1702. Min Act: -0.1700
Data Index: 2639045 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1702. Min Act: -0.1700
Data Index: 4521731 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1389. Min Act: -0.1700
Data Index: 6634864 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.1077. Min Act: -0.1700
Data Index: 1415095 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.0764. Min Act: -0.1700
Data Index: 4826462 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19