Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.4882. Min Act: -0.1700
Data Index: 1292605 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.5507. Min Act: -0.1700
Data Index: 3058686 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.5507. Min Act: -0.1700
Data Index: 6897011 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.4882. Min Act: -0.1700
Data Index: 5550976 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.4882. Min Act: -0.1700
Data Index: 4065897 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.4257. Min Act: -0.1700
Data Index: 3851063 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.4257. Min Act: -0.1700
Data Index: 6785835 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.3632. Min Act: -0.1700
Data Index: 6685802 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.3007. Min Act: -0.1700
Data Index: 3788263 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.3007. Min Act: -0.1700
Data Index: 4239899 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.3007. Min Act: -0.1700
Data Index: 8605230 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.1757. Min Act: -0.1700
Data Index: 3718756 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.1757. Min Act: -0.1700
Data Index: 2336850 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.1132. Min Act: -0.1700
Data Index: 990104 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.1132. Min Act: -0.1700
Data Index: 7659841 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.1132. Min Act: -0.1700
Data Index: 2979001 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.0507. Min Act: -0.1700
Data Index: 1413033 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.0507. Min Act: -0.1700
Data Index: 4944002 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5507. Min Range: -10.5507
Max Act: 10.0507. Min Act: -0.1700
Data Index: 50070 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5507. Min Range: -10.5507
Max Act: 9.9257. Min Act: -0.1700
Data Index: 3505583 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19