Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.4151. Min Act: -0.1700
Data Index: 5334419 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.3838. Min Act: -0.1700
Data Index: 8319675 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.3838. Min Act: -0.1700
Data Index: 8206768 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.2276. Min Act: -0.1700
Data Index: 1345240 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1963. Min Act: -0.1700
Data Index: 6466383 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1651. Min Act: -0.1700
Data Index: 7824117 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1651. Min Act: -0.1700
Data Index: 1973681 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1651. Min Act: -0.1700
Data Index: 3153381 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1338. Min Act: -0.1700
Data Index: 613367 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1338. Min Act: -0.1700
Data Index: 6991216 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1338. Min Act: -0.1700
Data Index: 6164145 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1026. Min Act: -0.1700
Data Index: 2891014 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1026. Min Act: -0.1700
Data Index: 1259660 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1026. Min Act: -0.1700
Data Index: 1974274 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.0713. Min Act: -0.1700
Data Index: 8577701 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.0713. Min Act: -0.1700
Data Index: 6915165 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.1026. Min Act: -0.1700
Data Index: 1071225 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.0713. Min Act: -0.1700
Data Index: 1896851 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4265919 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4151. Min Range: -5.4151
Max Act: 5.0401. Min Act: -0.1700
Data Index: 1984691 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19