Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5415 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.7049. Min Act: -0.1700
Data Index: 4741705 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.6112. Min Act: -0.1700
Data Index: 3813301 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.6112. Min Act: -0.1700
Data Index: 4173875 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.5486. Min Act: -0.1700
Data Index: 8247352 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.5174. Min Act: -0.1700
Data Index: 4239381 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.5174. Min Act: -0.1700
Data Index: 2784119 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.4861. Min Act: -0.1700
Data Index: 6634555 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.4549. Min Act: -0.1700
Data Index: 6416483 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.4549. Min Act: -0.1700
Data Index: 4299455 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.4236. Min Act: -0.1700
Data Index: 4016008 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3924. Min Act: -0.1700
Data Index: 443507 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.4236. Min Act: -0.1700
Data Index: 4458934 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3924. Min Act: -0.1700
Data Index: 4590000 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3924. Min Act: -0.1700
Data Index: 1631972 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3924. Min Act: -0.1700
Data Index: 8611330 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3611. Min Act: -0.1700
Data Index: 6993025 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3611. Min Act: -0.1700
Data Index: 6302306 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3611. Min Act: -0.1700
Data Index: 5231195 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3611. Min Act: -0.1700
Data Index: 6147738 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7049. Min Range: -4.7049
Max Act: 4.3611. Min Act: -0.1700
Data Index: 6052527 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19