Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0865. Min Act: -0.1700
Data Index: 1418905 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0240. Min Act: -0.1700
Data Index: 8627395 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0240. Min Act: -0.1700
Data Index: 4145523 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0865. Min Act: -0.1700
Data Index: 8646657 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9927. Min Act: -0.1700
Data Index: 355705 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0240. Min Act: -0.1700
Data Index: 573015 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0865. Min Range: -4.0865
Max Act: 4.0240. Min Act: -0.1700
Data Index: 968541 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9615. Min Act: -0.1700
Data Index: 673690 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9927. Min Act: -0.1700
Data Index: 1415149 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 7878178 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9615. Min Act: -0.1700
Data Index: 8719377 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 938826 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 2174438 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4600542 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9615. Min Act: -0.1700
Data Index: 8568957 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 8315999 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 2386026 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9302. Min Act: -0.1700
Data Index: 345444 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9615. Min Act: -0.1700
Data Index: 6359943 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0865. Min Range: -4.0865
Max Act: 3.9615. Min Act: -0.1700
Data Index: 5636260 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19