Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.5702. Min Act: -0.1700
Data Index: 2014765 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.3514. Min Act: -0.1700
Data Index: 4924360 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.3514. Min Act: -0.1700
Data Index: 6822485 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2889. Min Act: -0.1700
Data Index: 3264860 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2889. Min Act: -0.1700
Data Index: 1165658 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2577. Min Act: -0.1700
Data Index: 6812573 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2889. Min Act: -0.1700
Data Index: 6518257 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2264. Min Act: -0.1700
Data Index: 2195749 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2264. Min Act: -0.1700
Data Index: 3261643 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2264. Min Act: -0.1700
Data Index: 1361360 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2264. Min Act: -0.1700
Data Index: 4895355 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.2264. Min Act: -0.1700
Data Index: 4587093 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1639. Min Act: -0.1700
Data Index: 3467901 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1952. Min Act: -0.1700
Data Index: 5370579 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1952. Min Act: -0.1700
Data Index: 2252470 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1327. Min Act: -0.1700
Data Index: 4752004 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1327. Min Act: -0.1700
Data Index: 1872806 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1327. Min Act: -0.1700
Data Index: 6425148 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1327. Min Act: -0.1700
Data Index: 1329853 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5702. Min Range: -4.5702
Max Act: 4.1327. Min Act: -0.1700
Data Index: 4326185 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19