Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.6027. Min Act: -0.1700
Data Index: 4469799 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.5402. Min Act: -0.1700
Data Index: 4819325 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4777. Min Act: -0.1700
Data Index: 5930305 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.5402. Min Act: -0.1700
Data Index: 4687292 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4777. Min Act: -0.1700
Data Index: 5659756 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.5089. Min Act: -0.1700
Data Index: 5818736 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.5089. Min Act: -0.1700
Data Index: 6181993 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4464. Min Act: -0.1700
Data Index: 8022663 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4777. Min Act: -0.1700
Data Index: 8334495 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4777. Min Act: -0.1700
Data Index: 5897363 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4464. Min Act: -0.1700
Data Index: 6535923 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4152. Min Act: -0.1700
Data Index: 6795291 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4464. Min Act: -0.1700
Data Index: 2776459 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4464. Min Act: -0.1700
Data Index: 4946260 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4152. Min Act: -0.1700
Data Index: 5390276 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4152. Min Act: -0.1700
Data Index: 2855767 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4152. Min Act: -0.1700
Data Index: 361462 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.4152. Min Act: -0.1700
Data Index: 958133 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.2902. Min Act: -0.1700
Data Index: 6059048 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6027. Min Range: -4.6027
Max Act: 4.3839. Min Act: -0.1700
Data Index: 6468317 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19