Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.8293. Min Act: -0.1700
Data Index: 2682055 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2629081 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.6106. Min Act: -0.1700
Data Index: 489955 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.6418. Min Act: -0.1700
Data Index: 6741741 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.5793. Min Act: -0.1700
Data Index: 2682054 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.5793. Min Act: -0.1700
Data Index: 230222 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.5793. Min Act: -0.1700
Data Index: 4745400 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.5481. Min Act: -0.1700
Data Index: 2682052 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4543. Min Act: -0.1700
Data Index: 7559823 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4543. Min Act: -0.1700
Data Index: 7979418 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.3918. Min Act: -0.1700
Data Index: 3868036 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4231. Min Act: -0.1700
Data Index: 976365 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4231. Min Act: -0.1700
Data Index: 8533573 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4543. Min Act: -0.1700
Data Index: 6753100 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.4231. Min Act: -0.1700
Data Index: 7559822 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.3918. Min Act: -0.1700
Data Index: 6671280 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8163299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.3606. Min Act: -0.1700
Data Index: 6596352 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.3918. Min Act: -0.1700
Data Index: 4144975 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8293. Min Range: -5.8293
Max Act: 5.2981. Min Act: -0.1700
Data Index: 2150034 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19