Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0488. Min Range: -8.0488
Max Act: 8.0488. Min Act: -0.1700
Data Index: 6572446 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 1366495 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8925. Min Act: -0.1700
Data Index: 3741140 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 6361479 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8300. Min Act: -0.1700
Data Index: 4500479 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 5753229 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 4810854 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 7090877 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8613. Min Act: -0.1700
Data Index: 7469912 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8925. Min Act: -0.1700
Data Index: 3798142 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7363. Min Act: -0.1700
Data Index: 1084882 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7675. Min Act: -0.1700
Data Index: 720785 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7988. Min Act: -0.1700
Data Index: 5235335 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7988. Min Act: -0.1700
Data Index: 4271066 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.8925. Min Act: -0.1700
Data Index: 6977719 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7050. Min Act: -0.1700
Data Index: 4078834 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7675. Min Act: -0.1700
Data Index: 1316551 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7675. Min Act: -0.1700
Data Index: 7400589 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7675. Min Act: -0.1700
Data Index: 5926301 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0488. Min Range: -8.0488
Max Act: 7.7363. Min Act: -0.1700
Data Index: 3855044 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19