Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4743 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.5079. Min Act: -0.1700
Data Index: 6566483 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.4139. Min Act: -0.1700
Data Index: 1274644 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.3983. Min Act: -0.1700
Data Index: 1274639 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2727. Min Act: -0.1700
Data Index: 7765134 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2570. Min Act: -0.1700
Data Index: 7042936 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2256. Min Act: -0.1700
Data Index: 7163485 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2256. Min Act: -0.1700
Data Index: 7596844 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2256. Min Act: -0.1700
Data Index: 4906527 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.2099. Min Act: -0.1700
Data Index: 6552527 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1784. Min Act: -0.1700
Data Index: 718890 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1784. Min Act: -0.1700
Data Index: 3450876 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1784. Min Act: -0.1700
Data Index: 1839408 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1627. Min Act: -0.1700
Data Index: 1738962 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1627. Min Act: -0.1700
Data Index: 1669986 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1469. Min Act: -0.1700
Data Index: 4658301 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1469. Min Act: -0.1700
Data Index: 718886 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1469. Min Act: -0.1700
Data Index: 4640632 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1312. Min Act: -0.1700
Data Index: 6588886 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1154. Min Act: -0.1700
Data Index: 3087531 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5079. Min Range: -3.5079
Max Act: 3.1312. Min Act: -0.1700
Data Index: 7163479 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19