Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.4257. Min Act: -0.1700
Data Index: 2711746 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.3319. Min Act: -0.1700
Data Index: 5034857 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.3319. Min Act: -0.1700
Data Index: 306168 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.1444. Min Act: -0.1700
Data Index: 1191406 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.0507. Min Act: -0.1700
Data Index: 2214293 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 102404 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 8156992 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.0194. Min Act: -0.1700
Data Index: 7717423 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9882. Min Act: -0.1700
Data Index: 2753899 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 5557778 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 759437 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6980354 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9257. Min Act: -0.1700
Data Index: 157652 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 304679 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8944. Min Act: -0.1700
Data Index: 5810115 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8944. Min Act: -0.1700
Data Index: 8131544 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8944. Min Act: -0.1700
Data Index: 4898800 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8632. Min Act: -0.1700
Data Index: 5273919 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8632. Min Act: -0.1700
Data Index: 4885781 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8632. Min Act: -0.1700
Data Index: 1104725 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19