Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.5270. Min Act: -0.1700
Data Index: 4430383 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4957. Min Act: -0.1700
Data Index: 287157 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4957. Min Act: -0.1700
Data Index: 525319 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4330. Min Act: -0.1700
Data Index: 6049192 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4330. Min Act: -0.1700
Data Index: 33097 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4487. Min Act: -0.1700
Data Index: 598586 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4174. Min Act: -0.1700
Data Index: 5078222 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.4017. Min Act: -0.1700
Data Index: 7304517 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3860. Min Act: -0.1700
Data Index: 4373321 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3703. Min Act: -0.1700
Data Index: 3918661 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3546. Min Act: -0.1700
Data Index: 5931042 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3546. Min Act: -0.1700
Data Index: 6242064 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3233. Min Act: -0.1700
Data Index: 4345626 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3390. Min Act: -0.1700
Data Index: 1480163 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3233. Min Act: -0.1700
Data Index: 568335 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3233. Min Act: -0.1700
Data Index: 3566533 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3390. Min Act: -0.1700
Data Index: 578629 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3233. Min Act: -0.1700
Data Index: 4462943 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3076. Min Act: -0.1700
Data Index: 184053 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5270. Min Range: -3.5270
Max Act: 3.3076. Min Act: -0.1700
Data Index: 2038090 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19