Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.5120. Min Act: -0.1700
Data Index: 5948388 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.5120. Min Act: -0.1700
Data Index: 7530096 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.4495. Min Act: -0.1700
Data Index: 2211870 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.4495. Min Act: -0.1700
Data Index: 3773487 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.4182. Min Act: -0.1700
Data Index: 3648151 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.4182. Min Act: -0.1700
Data Index: 6504083 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3870. Min Act: -0.1700
Data Index: 6588703 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3870. Min Act: -0.1700
Data Index: 881786 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3557. Min Act: -0.1700
Data Index: 881787 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3245. Min Act: -0.1700
Data Index: 4383276 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 6850870 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3245. Min Act: -0.1700
Data Index: 7433730 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 7056718 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 4465755 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 881788 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.3245. Min Act: -0.1700
Data Index: 785724 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 5464984 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 785723 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 3062538 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5120. Min Range: -4.5120
Max Act: 4.2932. Min Act: -0.1700
Data Index: 4026702 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19