Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.1747. Min Act: -0.1700
Data Index: 6837521 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0809. Min Act: -0.1700
Data Index: 6867775 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0809. Min Act: -0.1700
Data Index: 5800167 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0497. Min Act: -0.1700
Data Index: 8792787 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0497. Min Act: -0.1700
Data Index: 1923533 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0497. Min Act: -0.1700
Data Index: 6582340 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0184. Min Act: -0.1700
Data Index: 132676 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 7441243 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9872. Min Act: -0.1700
Data Index: 4625030 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 8716586 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 1891111 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 3825592 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 2993477 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 7023041 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 1927101 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2289249 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 4965912 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 8682265 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.8934. Min Act: -0.1700
Data Index: 1393862 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2702476 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19