Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.6945. Min Act: -0.1700
Data Index: 297886 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.6008. Min Act: -0.1700
Data Index: 2880240 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.6008. Min Act: -0.1700
Data Index: 792385 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.6008. Min Act: -0.1700
Data Index: 4859662 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.5695. Min Act: -0.1700
Data Index: 2318728 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.5383. Min Act: -0.1700
Data Index: 371227 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.5383. Min Act: -0.1700
Data Index: 6959410 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.5070. Min Act: -0.1700
Data Index: 7829283 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4758. Min Act: -0.1700
Data Index: 3465696 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4758. Min Act: -0.1700
Data Index: 5252511 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4758. Min Act: -0.1700
Data Index: 790583 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4758. Min Act: -0.1699
Data Index: 6253018 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4445. Min Act: -0.1700
Data Index: 7665058 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4445. Min Act: -0.1700
Data Index: 8418327 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 7080504 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 1722562 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 2697440 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 42616 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 1433562 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6945. Min Range: -5.6945
Max Act: 5.4133. Min Act: -0.1700
Data Index: 2227662 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19