Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 288 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.6009. Min Act: -0.1700
Data Index: 3654382 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.5659. Min Act: -0.1700
Data Index: 5075327 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.5133. Min Act: -0.1699
Data Index: 3682839 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.5133. Min Act: -0.1699
Data Index: 3656072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4958. Min Act: -0.1700
Data Index: 1395339 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4958. Min Act: -0.1700
Data Index: 7389578 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4782. Min Act: -0.1700
Data Index: 4624506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4782. Min Act: -0.1700
Data Index: 196407 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4518. Min Act: -0.1699
Data Index: 4630014 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4606. Min Act: -0.1700
Data Index: 191517 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4518. Min Act: -0.1700
Data Index: 2613216 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4430. Min Act: -0.1700
Data Index: 5263586 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4518. Min Act: -0.1700
Data Index: 7967556 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4518. Min Act: -0.1700
Data Index: 6359789 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4342. Min Act: -0.1700
Data Index: 2536574 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4430. Min Act: -0.1700
Data Index: 3046492 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4342. Min Act: -0.1700
Data Index: 6876129 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4430. Min Act: -0.1700
Data Index: 740910 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4254. Min Act: -0.1700
Data Index: 5441603 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6009. Min Range: -1.6009
Max Act: 1.4342. Min Act: -0.1700
Data Index: 5254201 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19