Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1240 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.5195. Min Act: -0.1700
Data Index: 4828711 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.2382. Min Act: -0.1700
Data Index: 716670 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.1757. Min Act: -0.1700
Data Index: 8573201 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0507. Min Act: -0.1700
Data Index: 1176805 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0819. Min Act: -0.1700
Data Index: 6107332 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0194. Min Act: -0.1700
Data Index: 838925 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0194. Min Act: -0.1700
Data Index: 133224 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0194. Min Act: -0.1700
Data Index: 7929042 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0194. Min Act: -0.1700
Data Index: 6292984 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9882. Min Act: -0.1700
Data Index: 2958771 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5195. Min Range: -4.5195
Max Act: 4.0194. Min Act: -0.1700
Data Index: 5206193 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9256. Min Act: -0.1700
Data Index: 5618402 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9569. Min Act: -0.1700
Data Index: 2830298 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9882. Min Act: -0.1700
Data Index: 7455797 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9569. Min Act: -0.1700
Data Index: 1127754 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9256. Min Act: -0.1700
Data Index: 7827458 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9256. Min Act: -0.1700
Data Index: 5689940 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9256. Min Act: -0.1700
Data Index: 841375 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.9569. Min Act: -0.1700
Data Index: 7136668 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5195. Min Range: -4.5195
Max Act: 3.8944. Min Act: -0.1700
Data Index: 107532 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19