Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.6427. Min Act: -0.1700
Data Index: 18089 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.6115. Min Act: -0.1700
Data Index: 990721 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.5177. Min Act: -0.1700
Data Index: 2986778 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.4240. Min Act: -0.1700
Data Index: 6939597 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.3302. Min Act: -0.1700
Data Index: 5309045 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.3302. Min Act: -0.1700
Data Index: 6931853 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.2677. Min Act: -0.1700
Data Index: 6939598 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.2365. Min Act: -0.1700
Data Index: 6104553 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.2052. Min Act: -0.1700
Data Index: 3052896 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.2052. Min Act: -0.1700
Data Index: 7799686 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1739. Min Act: -0.1700
Data Index: 4396257 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1427. Min Act: -0.1700
Data Index: 7799687 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1427. Min Act: -0.1700
Data Index: 6939599 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1114. Min Act: -0.1700
Data Index: 6722210 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1114. Min Act: -0.1700
Data Index: 2697098 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.1114. Min Act: -0.1700
Data Index: 708770 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.0489. Min Act: -0.1700
Data Index: 707065 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.0489. Min Act: -0.1700
Data Index: 5647859 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.0802. Min Act: -0.1700
Data Index: 158336 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6427. Min Range: -4.6427
Max Act: 4.0489. Min Act: -0.1700
Data Index: 5176147 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19