Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1947. Min Range: -6.1947
Max Act: 6.1947. Min Act: -0.1690
Data Index: 1925302 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.9134. Min Act: -0.1700
Data Index: 8482449 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.8509. Min Act: -0.1674
Data Index: 1925309 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.7259. Min Act: -0.1636
Data Index: 1925303 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.6947. Min Act: -0.1700
Data Index: 2442181 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.6634. Min Act: -0.1700
Data Index: 6061165 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.6009. Min Act: -0.1700
Data Index: 5194725 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 1260554 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.6009. Min Act: -0.1700
Data Index: 416031 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 3028546 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 6463749 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.6009. Min Act: -0.1700
Data Index: 8151059 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 4180650 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 8748383 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 3163514 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5384. Min Act: -0.1700
Data Index: 885201 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 3757361 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4613354 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5384. Min Act: -0.1700
Data Index: 2376506 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1947. Min Range: -6.1947
Max Act: 5.5384. Min Act: -0.1700
Data Index: 3279901 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19