Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4317 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4862. Min Act: -0.1700
Data Index: 8219734 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4862. Min Act: -0.1700
Data Index: 8432378 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4550. Min Act: -0.1700
Data Index: 1105752 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4237. Min Act: -0.1700
Data Index: 8318786 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6723460 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4237. Min Act: -0.1700
Data Index: 3200219 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3925. Min Act: -0.1700
Data Index: 8671114 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4237. Min Act: -0.1700
Data Index: 7150752 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3612. Min Act: -0.1700
Data Index: 1707747 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3925. Min Act: -0.1700
Data Index: 4140409 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3925. Min Act: -0.1700
Data Index: 3818352 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3925. Min Act: -0.1700
Data Index: 1099172 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3612. Min Act: -0.1700
Data Index: 6060237 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3612. Min Act: -0.1700
Data Index: 1433187 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 4984314 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2708299 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 8306783 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2397264 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2888716 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3300. Min Act: -0.1700
Data Index: 5439273 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19