Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1702 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.2802. Min Act: -0.1700
Data Index: 8046058 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.2802. Min Act: -0.1700
Data Index: 4901011 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.2177. Min Act: -0.1700
Data Index: 1727933 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.0614. Min Act: -0.1700
Data Index: 3819141 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.0927. Min Act: -0.1700
Data Index: 8700762 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.0302. Min Act: -0.1700
Data Index: 2320018 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9677. Min Act: -0.1700
Data Index: 6562483 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9364. Min Act: -0.1700
Data Index: 1926220 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9364. Min Act: -0.1700
Data Index: 8395119 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7316079 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9052. Min Act: -0.1700
Data Index: 2072072 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8427. Min Act: -0.1700
Data Index: 3094959 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8427. Min Act: -0.1700
Data Index: 7999579 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8114. Min Act: -0.1700
Data Index: 2218826 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8114. Min Act: -0.1700
Data Index: 1252965 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7802. Min Act: -0.1700
Data Index: 5719077 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8427. Min Act: -0.1700
Data Index: 2928607 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7489. Min Act: -0.1700
Data Index: 1765705 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7802. Min Act: -0.1700
Data Index: 7978058 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7802. Min Act: -0.1700
Data Index: 3949383 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19