Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.2378. Min Act: -0.1700
Data Index: 5667586 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.2378. Min Act: -0.1700
Data Index: 1301093 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.1128. Min Act: -0.1700
Data Index: 7808515 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.1128. Min Act: -0.1700
Data Index: 2969856 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.0815. Min Act: -0.1700
Data Index: 5170464 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2378. Min Range: -7.2378
Max Act: 7.0190. Min Act: -0.1700
Data Index: 6398185 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.9565. Min Act: -0.1700
Data Index: 2806206 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.9565. Min Act: -0.1700
Data Index: 1330637 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.9565. Min Act: -0.1700
Data Index: 8624315 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8940. Min Act: -0.1700
Data Index: 3689591 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8940. Min Act: -0.1700
Data Index: 6948931 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8940. Min Act: -0.1700
Data Index: 2605963 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8315. Min Act: -0.1700
Data Index: 2805291 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8315. Min Act: -0.1700
Data Index: 4358834 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.8003. Min Act: -0.1700
Data Index: 587434 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.7690. Min Act: -0.1700
Data Index: 1939354 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.7378. Min Act: -0.1700
Data Index: 8609769 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.7378. Min Act: -0.1700
Data Index: 1716690 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.7378. Min Act: -0.1700
Data Index: 4886971 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2378. Min Range: -7.2378
Max Act: 6.7065. Min Act: -0.1700
Data Index: 2417242 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19