Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5718 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1261. Min Range: -7.1261
Max Act: 7.1261. Min Act: -0.1700
Data Index: 7653332 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.9386. Min Act: -0.1700
Data Index: 4694343 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.9698. Min Act: -0.1700
Data Index: 8018366 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.8761. Min Act: -0.1700
Data Index: 7261612 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.8448. Min Act: -0.1700
Data Index: 4491587 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.8761. Min Act: -0.1700
Data Index: 2996540 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.8136. Min Act: -0.1700
Data Index: 13178 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.7511. Min Act: -0.1700
Data Index: 615047 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.7823. Min Act: -0.1700
Data Index: 2029627 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.7198. Min Act: -0.1700
Data Index: 6214164 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6886. Min Act: -0.1700
Data Index: 253394 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6573. Min Act: -0.1700
Data Index: 8331161 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6573. Min Act: -0.1700
Data Index: 7677292 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6573. Min Act: -0.1700
Data Index: 1884185 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6573. Min Act: -0.1700
Data Index: 2830623 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6261. Min Act: -0.1700
Data Index: 92961 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.6261. Min Act: -0.1700
Data Index: 368965 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.5636. Min Act: -0.1700
Data Index: 4143595 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.5323. Min Act: -0.1700
Data Index: 3460938 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1261. Min Range: -7.1261
Max Act: 6.5011. Min Act: -0.1700
Data Index: 7027549 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19