Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0080. Min Range: -5.0080
Max Act: 5.0080. Min Act: -0.1700
Data Index: 1965195 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0080. Min Range: -5.0080
Max Act: 5.0080. Min Act: -0.1700
Data Index: 2806280 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9455. Min Act: -0.1700
Data Index: 5471222 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9767. Min Act: -0.1700
Data Index: 4419286 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0080. Min Range: -5.0080
Max Act: 5.0080. Min Act: -0.1700
Data Index: 1939065 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9455. Min Act: -0.1700
Data Index: 3560824 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 2490252 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9455. Min Act: -0.1700
Data Index: 2291420 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 3657686 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 8793207 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 7298467 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 7277671 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 7058506 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9455. Min Act: -0.1700
Data Index: 658008 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 2494033 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 6722119 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 5069448 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 1572789 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.9142. Min Act: -0.1700
Data Index: 3824120 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0080. Min Range: -5.0080
Max Act: 4.8830. Min Act: -0.1700
Data Index: 1993762 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19