Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0057. Min Range: -6.0057
Max Act: 6.0057. Min Act: -0.1700
Data Index: 979586 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.9119. Min Act: -0.1700
Data Index: 2946612 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.8494. Min Act: -0.1700
Data Index: 5947029 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.7869. Min Act: -0.1700
Data Index: 3200466 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.7244. Min Act: -0.1700
Data Index: 5315944 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6484070 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6932. Min Act: -0.1700
Data Index: 7244725 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6932. Min Act: -0.1700
Data Index: 1348712 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6619. Min Act: -0.1700
Data Index: 8115504 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6619. Min Act: -0.1700
Data Index: 2683697 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6619. Min Act: -0.1700
Data Index: 2855261 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6619. Min Act: -0.1700
Data Index: 8585651 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6307. Min Act: -0.1700
Data Index: 3726083 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6307. Min Act: -0.1700
Data Index: 6685888 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.6307. Min Act: -0.1700
Data Index: 3756501 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.5682. Min Act: -0.1700
Data Index: 8665996 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.5994. Min Act: -0.1700
Data Index: 6740544 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.5994. Min Act: -0.1700
Data Index: 411597 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6487432 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0057. Min Range: -6.0057
Max Act: 5.5682. Min Act: -0.1700
Data Index: 260305 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19