Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4696 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.9802. Min Act: -0.1699
Data Index: 6128849 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.9489. Min Act: -0.1700
Data Index: 3481917 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.9489. Min Act: -0.1700
Data Index: 6059607 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.8239. Min Act: -0.1700
Data Index: 4132998 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7927. Min Act: -0.1700
Data Index: 362176 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 89932 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7927. Min Act: -0.1700
Data Index: 136272 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7927. Min Act: -0.1700
Data Index: 3838702 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 3366143 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1680531 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 6347733 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 3841680 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 8629404 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 7273247 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7302. Min Act: -0.1700
Data Index: 5862174 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1699
Data Index: 350051 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7302. Min Act: -0.1700
Data Index: 6524504 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.7614. Min Act: -0.1700
Data Index: 3950557 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.6677. Min Act: -0.1700
Data Index: 2141428 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9802. Min Range: -5.9802
Max Act: 5.6989. Min Act: -0.1700
Data Index: 6471737 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19