Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.4549. Min Act: -0.1700
Data Index: 2603671 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.1424. Min Act: -0.1700
Data Index: 7871240 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.1424. Min Act: -0.1700
Data Index: 3548556 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.2049. Min Act: -0.1700
Data Index: 53998 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.1424. Min Act: -0.1700
Data Index: 7871242 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.0174. Min Act: -0.1700
Data Index: 6190944 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.0174. Min Act: -0.1700
Data Index: 6190946 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.0799. Min Act: -0.1700
Data Index: 560957 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.9549. Min Act: -0.1700
Data Index: 6497334 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.0174. Min Act: -0.1700
Data Index: 3819316 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4549. Min Range: -8.4549
Max Act: 8.0174. Min Act: -0.1700
Data Index: 6497331 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.9549. Min Act: -0.1700
Data Index: 7201753 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.9549. Min Act: -0.1700
Data Index: 2236149 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.9549. Min Act: -0.1700
Data Index: 7871245 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 2236150 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 2869297 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 7281264 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 3548562 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 6119383 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4549. Min Range: -8.4549
Max Act: 7.8924. Min Act: -0.1700
Data Index: 4649916 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19