Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8168. Min Act: -0.1700
Data Index: 3236606 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8168. Min Act: -0.1700
Data Index: 1683510 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8009. Min Act: -0.1700
Data Index: 534567 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8009. Min Act: -0.1700
Data Index: 3311668 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7849. Min Act: -0.1700
Data Index: 834379 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8009. Min Act: -0.1700
Data Index: 4670254 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7849. Min Act: -0.1700
Data Index: 8721288 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7849. Min Act: -0.1700
Data Index: 2968156 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 2794201 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 4665175 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 4578974 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 2918835 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 6132513 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 4821724 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 2096562 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 5837367 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 1529954 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 1101038 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 4146097 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 5663024 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19