Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1305 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.7929. Min Act: -0.1700
Data Index: 8087379 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.4491. Min Act: -0.1700
Data Index: 4061816 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.3866. Min Act: -0.1700
Data Index: 7283707 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.3241. Min Act: -0.1700
Data Index: 598805 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.3241. Min Act: -0.1700
Data Index: 7962870 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.3241. Min Act: -0.1700
Data Index: 7725071 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2929. Min Act: -0.1700
Data Index: 6072246 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2616. Min Act: -0.1700
Data Index: 8396673 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2616. Min Act: -0.1700
Data Index: 7002264 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2616. Min Act: -0.1700
Data Index: 4407345 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2616. Min Act: -0.1700
Data Index: 3835087 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2304. Min Act: -0.1700
Data Index: 6947892 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2304. Min Act: -0.1700
Data Index: 7141570 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1679. Min Act: -0.1700
Data Index: 8821248 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.2304. Min Act: -0.1700
Data Index: 7417512 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1679. Min Act: -0.1700
Data Index: 1572669 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1679. Min Act: -0.1700
Data Index: 5541104 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1366. Min Act: -0.1700
Data Index: 673634 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1366. Min Act: -0.1700
Data Index: 5241147 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7929. Min Range: -6.7929
Max Act: 6.1366. Min Act: -0.1700
Data Index: 980818 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19