Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0195. Min Range: -5.0195
Max Act: 5.0195. Min Act: -0.1700
Data Index: 4374277 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.9257. Min Act: -0.1700
Data Index: 4568878 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8945. Min Act: -0.1700
Data Index: 7071621 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8945. Min Act: -0.1700
Data Index: 8746087 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.9257. Min Act: -0.1700
Data Index: 4975641 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8320. Min Act: -0.1700
Data Index: 3063677 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8632. Min Act: -0.1700
Data Index: 3864593 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8632. Min Act: -0.1700
Data Index: 4339665 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8320. Min Act: -0.1700
Data Index: 2236602 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8320. Min Act: -0.1700
Data Index: 940713 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 8140415 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8007. Min Act: -0.1700
Data Index: 2914674 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8007. Min Act: -0.1700
Data Index: 4017316 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8007. Min Act: -0.1700
Data Index: 3586991 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.8320. Min Act: -0.1700
Data Index: 5812304 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 6638732 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 6268071 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 4750969 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 6933520 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0195. Min Range: -5.0195
Max Act: 4.7695. Min Act: -0.1700
Data Index: 1766535 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19