Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 1849307 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.5674. Min Act: -0.1700
Data Index: 2062133 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.4424. Min Act: -0.1700
Data Index: 2675809 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.3799. Min Act: -0.1700
Data Index: 5459240 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.2237. Min Act: -0.1700
Data Index: 3255609 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.1924. Min Act: -0.1700
Data Index: 8272964 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.1612. Min Act: -0.1700
Data Index: 20283 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.1299. Min Act: -0.1700
Data Index: 3864748 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.0674. Min Act: -0.1700
Data Index: 6505718 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.1299. Min Act: -0.1700
Data Index: 841693 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.0987. Min Act: -0.1700
Data Index: 5097693 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.0674. Min Act: -0.1700
Data Index: 8796803 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.0049. Min Act: -0.1700
Data Index: 4809512 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7549. Min Range: -8.7549
Max Act: 8.0049. Min Act: -0.1700
Data Index: 3605797 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.9737. Min Act: -0.1700
Data Index: 6475375 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.9737. Min Act: -0.1700
Data Index: 1937044 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.9424. Min Act: -0.1700
Data Index: 7513377 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.9112. Min Act: -0.1700
Data Index: 3074741 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.8799. Min Act: -0.1700
Data Index: 1937068 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7549. Min Range: -8.7549
Max Act: 7.8487. Min Act: -0.1700
Data Index: 5880018 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19