Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4916 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.3246. Min Act: -0.1700
Data Index: 5847175 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2934. Min Act: -0.1700
Data Index: 31400 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2934. Min Act: -0.1700
Data Index: 4421474 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7450359 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2621. Min Act: -0.1700
Data Index: 8458546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2621. Min Act: -0.1700
Data Index: 1002661 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2621. Min Act: -0.1700
Data Index: 4860420 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2308. Min Act: -0.1700
Data Index: 8429725 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8228104 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2308. Min Act: -0.1700
Data Index: 1200173 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2308. Min Act: -0.1700
Data Index: 8557054 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2308. Min Act: -0.1700
Data Index: 2849251 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1996. Min Act: -0.1700
Data Index: 2104827 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.2308. Min Act: -0.1700
Data Index: 1537537 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4772731 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1996. Min Act: -0.1700
Data Index: 5671822 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1683. Min Act: -0.1700
Data Index: 1700285 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1683. Min Act: -0.1700
Data Index: 1002663 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3117518 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3246. Min Range: -4.3246
Max Act: 4.1683. Min Act: -0.1700
Data Index: 8250214 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19