Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.2190. Min Act: -0.1700
Data Index: 1448319 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.1253. Min Act: -0.1700
Data Index: 5274174 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.1253. Min Act: -0.1700
Data Index: 870510 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.1565. Min Act: -0.1700
Data Index: 966548 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.0003. Min Act: -0.1700
Data Index: 1712011 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.0003. Min Act: -0.1700
Data Index: 7122011 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.0003. Min Act: -0.1700
Data Index: 2887455 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2190. Min Range: -6.2190
Max Act: 6.0315. Min Act: -0.1700
Data Index: 5659961 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9690. Min Act: -0.1700
Data Index: 811506 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5204715 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9378. Min Act: -0.1700
Data Index: 1107032 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9378. Min Act: -0.1700
Data Index: 1753054 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.8753. Min Act: -0.1700
Data Index: 3901553 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9065. Min Act: -0.1700
Data Index: 3312237 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9065. Min Act: -0.1700
Data Index: 2642124 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.9065. Min Act: -0.1700
Data Index: 3221219 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.8440. Min Act: -0.1700
Data Index: 2451854 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.8753. Min Act: -0.1700
Data Index: 261628 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.8753. Min Act: -0.1700
Data Index: 4646832 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2190. Min Range: -6.2190
Max Act: 5.8753. Min Act: -0.1700
Data Index: 1889268 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19