Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.3171. Min Act: -0.1700
Data Index: 8408058 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.2546. Min Act: -0.1700
Data Index: 80242 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.2234. Min Act: -0.1700
Data Index: 6571598 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1608. Min Act: -0.1700
Data Index: 2108509 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1296. Min Act: -0.1700
Data Index: 6396473 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1608. Min Act: -0.1700
Data Index: 5516616 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1296. Min Act: -0.1700
Data Index: 1027242 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1296. Min Act: -0.1700
Data Index: 2328771 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1296. Min Act: -0.1700
Data Index: 1473566 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.1296. Min Act: -0.1700
Data Index: 7113811 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0983. Min Act: -0.1700
Data Index: 4381691 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0671. Min Act: -0.1700
Data Index: 8251171 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0671. Min Act: -0.1700
Data Index: 5344393 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0671. Min Act: -0.1700
Data Index: 4561890 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0358. Min Act: -0.1700
Data Index: 1216708 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0671. Min Act: -0.1700
Data Index: 6054029 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0358. Min Act: -0.1700
Data Index: 1561139 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0358. Min Act: -0.1700
Data Index: 3175689 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0046. Min Act: -0.1700
Data Index: 3261824 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3171. Min Range: -4.3171
Max Act: 4.0671. Min Act: -0.1700
Data Index: 5554768 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19