Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.3175. Min Act: -0.1700
Data Index: 7038070 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2862. Min Act: -0.1700
Data Index: 2711323 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.3175. Min Act: -0.1700
Data Index: 3369872 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.3175. Min Act: -0.1700
Data Index: 6902016 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2862. Min Act: -0.1700
Data Index: 6618670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2550. Min Act: -0.1700
Data Index: 950316 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2237. Min Act: -0.1700
Data Index: 6800003 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2550. Min Act: -0.1700
Data Index: 3679852 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2237. Min Act: -0.1700
Data Index: 4108678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1925. Min Act: -0.1700
Data Index: 1572671 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.2237. Min Act: -0.1700
Data Index: 4895546 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1612. Min Act: -0.1700
Data Index: 6989395 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1925. Min Act: -0.1700
Data Index: 3400384 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1300. Min Act: -0.1700
Data Index: 7188758 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1300. Min Act: -0.1700
Data Index: 5179317 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1300. Min Act: -0.1700
Data Index: 4895545 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1612. Min Act: -0.1700
Data Index: 3589046 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1300. Min Act: -0.1700
Data Index: 381357 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.1300. Min Act: -0.1700
Data Index: 2817535 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3175. Min Range: -4.3175
Max Act: 4.0987. Min Act: -0.1700
Data Index: 2349728 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19