Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5811 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0823. Min Range: -7.0823
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6662960 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.7073. Min Act: -0.1700
Data Index: 5676158 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.6136. Min Act: -0.1700
Data Index: 2237077 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.6448. Min Act: -0.1700
Data Index: 2952377 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.6136. Min Act: -0.1700
Data Index: 3375500 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.6136. Min Act: -0.1700
Data Index: 8306776 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 8255554 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 1777176 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 3426056 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5511. Min Act: -0.1700
Data Index: 8802615 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5511. Min Act: -0.1700
Data Index: 1421199 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5198. Min Act: -0.1700
Data Index: 280963 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.5198. Min Act: -0.1700
Data Index: 1312364 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4886. Min Act: -0.1700
Data Index: 5262511 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4886. Min Act: -0.1700
Data Index: 7460419 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4573. Min Act: -0.1700
Data Index: 5628405 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4573. Min Act: -0.1700
Data Index: 3031570 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4261. Min Act: -0.1700
Data Index: 3369795 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4261. Min Act: -0.1700
Data Index: 7794121 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0823. Min Range: -7.0823
Max Act: 6.4261. Min Act: -0.1700
Data Index: 2765997 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19