Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.6932. Min Act: -0.1700
Data Index: 3413995 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.6307. Min Act: -0.1700
Data Index: 8196885 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.5057. Min Act: -0.1700
Data Index: 2958945 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.3807. Min Act: -0.1700
Data Index: 2691095 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.3182. Min Act: -0.1700
Data Index: 3217088 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.0682. Min Act: -0.1700
Data Index: 1727324 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6932. Min Range: -11.6932
Max Act: 11.0057. Min Act: -0.1700
Data Index: 8145894 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.8182. Min Act: -0.1700
Data Index: 8387091 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.8182. Min Act: -0.1700
Data Index: 8347157 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.8182. Min Act: -0.1700
Data Index: 5718543 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.7557. Min Act: -0.1700
Data Index: 5906840 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.7557. Min Act: -0.1700
Data Index: 8163699 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6932. Min Act: -0.1700
Data Index: 978467 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6307. Min Act: -0.1700
Data Index: 2446160 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6307. Min Act: -0.1700
Data Index: 8370843 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6307. Min Act: -0.1700
Data Index: 1163281 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6307. Min Act: -0.1700
Data Index: 4089357 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6932. Min Act: -0.1700
Data Index: 560068 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.6307. Min Act: -0.1700
Data Index: 5348764 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6932. Min Range: -11.6932
Max Act: 10.5682. Min Act: -0.1700
Data Index: 805574 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19