Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1015. Min Range: -7.1015
Max Act: 7.1015. Min Act: -0.1700
Data Index: 525578 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.8203. Min Act: -0.1700
Data Index: 4491331 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 7122403 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 1948671 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 3003178 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.3203. Min Act: -0.1700
Data Index: 7759056 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.2578. Min Act: -0.1700
Data Index: 5741245 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.2578. Min Act: -0.1700
Data Index: 227532 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.1953. Min Act: -0.1700
Data Index: 254480 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.1953. Min Act: -0.1700
Data Index: 6633481 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 8511912 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 1925029 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1191493 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7447652 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.0703. Min Act: -0.1700
Data Index: 3270019 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.0703. Min Act: -0.1700
Data Index: 2837714 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.0078. Min Act: -0.1700
Data Index: 7520529 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1015. Min Range: -7.1015
Max Act: 6.0078. Min Act: -0.1700
Data Index: 5600267 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1015. Min Range: -7.1015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3426435 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1015. Min Range: -7.1015
Max Act: 5.9453. Min Act: -0.1700
Data Index: 1122716 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19