Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5971 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1184. Min Range: -4.1184
Max Act: 4.1184. Min Act: -0.1700
Data Index: 8450492 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1184. Min Range: -4.1184
Max Act: 4.0558. Min Act: -0.1700
Data Index: 6944879 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1184. Min Range: -4.1184
Max Act: 4.0558. Min Act: -0.1700
Data Index: 7956256 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9933. Min Act: -0.1700
Data Index: 5512237 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9621. Min Act: -0.1700
Data Index: 3485574 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9621. Min Act: -0.1700
Data Index: 7278780 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9308. Min Act: -0.1700
Data Index: 5995269 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9308. Min Act: -0.1700
Data Index: 6250459 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8995. Min Act: -0.1700
Data Index: 22951 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.9308. Min Act: -0.1700
Data Index: 7771951 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8995. Min Act: -0.1700
Data Index: 3890993 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 7988419 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 7085530 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 4717018 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 5134662 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 8254553 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8683. Min Act: -0.1700
Data Index: 2644155 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8370. Min Act: -0.1700
Data Index: 5263499 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8370. Min Act: -0.1700
Data Index: 4424220 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1184. Min Range: -4.1184
Max Act: 3.8057. Min Act: -0.1700
Data Index: 6214192 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19