Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3910. Min Range: -4.3910
Max Act: 4.3910. Min Act: -0.1700
Data Index: 7364954 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3910. Min Range: -4.3910
Max Act: 4.0784. Min Act: -0.1700
Data Index: 1082114 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3910. Min Range: -4.3910
Max Act: 4.0784. Min Act: -0.1700
Data Index: 7364953 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3910. Min Range: -4.3910
Max Act: 4.0472. Min Act: -0.1700
Data Index: 1660810 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3910. Min Range: -4.3910
Max Act: 4.0472. Min Act: -0.1700
Data Index: 3977697 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.9847. Min Act: -0.1700
Data Index: 6599833 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.9534. Min Act: -0.1700
Data Index: 4128689 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.9534. Min Act: -0.1700
Data Index: 5878417 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.9534. Min Act: -0.1700
Data Index: 5798318 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.8909. Min Act: -0.1700
Data Index: 182833 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.8596. Min Act: -0.1700
Data Index: 2385354 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7971. Min Act: -0.1700
Data Index: 5251640 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.8283. Min Act: -0.1700
Data Index: 6661379 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.8283. Min Act: -0.1700
Data Index: 2285529 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7971. Min Act: -0.1700
Data Index: 3378764 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7971. Min Act: -0.1700
Data Index: 6599826 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7971. Min Act: -0.1700
Data Index: 7627302 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7658. Min Act: -0.1700
Data Index: 5430878 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7658. Min Act: -0.1700
Data Index: 3694072 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3910. Min Range: -4.3910
Max Act: 3.7658. Min Act: -0.1700
Data Index: 882897 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19