Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5568 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.4029. Min Act: -0.1700
Data Index: 8776153 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.3404. Min Act: -0.1700
Data Index: 6452706 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.2466. Min Act: -0.1700
Data Index: 6150645 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.0904. Min Act: -0.1700
Data Index: 1219890 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.0904. Min Act: -0.1700
Data Index: 2034399 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.0279. Min Act: -0.1700
Data Index: 8483086 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9966. Min Act: -0.1700
Data Index: 1685683 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9966. Min Act: -0.1700
Data Index: 3093569 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 7703608 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 6326941 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 5172364 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 5101666 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 4979094 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 1807713 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 5181010 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9029. Min Act: -0.1700
Data Index: 208201 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 1839799 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 1938593 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 2673711 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 3053935 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19