Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.6330. Min Act: -0.1700
Data Index: 4146773 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5778. Min Act: -0.1700
Data Index: 739944 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5622. Min Act: -0.1700
Data Index: 4503819 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5700. Min Act: -0.1700
Data Index: 7997855 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5622. Min Act: -0.1698
Data Index: 3563771 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5622. Min Act: -0.1700
Data Index: 3842496 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5545. Min Act: -0.1700
Data Index: 3289520 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5545. Min Act: -0.1700
Data Index: 739943 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5468. Min Act: -0.1700
Data Index: 1715453 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5468. Min Act: -0.1700
Data Index: 4614602 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5391. Min Act: -0.1700
Data Index: 830681 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5391. Min Act: -0.1700
Data Index: 37503 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5315. Min Act: -0.1700
Data Index: 739945 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5163. Min Act: -0.1700
Data Index: 2059916 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5163. Min Act: -0.1700
Data Index: 6176169 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5012. Min Act: -0.1700
Data Index: 8643359 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5012. Min Act: -0.1700
Data Index: 4146775 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5012. Min Act: -0.1700
Data Index: 37502 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5012. Min Act: -0.1700
Data Index: 3537088 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6330. Min Range: -0.6330
Max Act: 0.5012. Min Act: -0.1700
Data Index: 408601 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19