Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4998. Min Act: -0.1700
Data Index: 5124032 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4214. Min Act: -0.1700
Data Index: 6864912 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4371. Min Act: -0.1700
Data Index: 3566053 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3430. Min Act: -0.1700
Data Index: 4143665 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3430. Min Act: -0.1700
Data Index: 7813297 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3116. Min Act: -0.1700
Data Index: 7411911 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3273. Min Act: -0.1700
Data Index: 1249020 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3273. Min Act: -0.1700
Data Index: 8418347 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3430. Min Act: -0.1700
Data Index: 1165075 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3116. Min Act: -0.1700
Data Index: 5003141 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2959. Min Act: -0.1700
Data Index: 4934613 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3116. Min Act: -0.1700
Data Index: 1684478 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2959. Min Act: -0.1700
Data Index: 7929963 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2645. Min Act: -0.1700
Data Index: 2736040 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2802. Min Act: -0.1700
Data Index: 569289 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2645. Min Act: -0.1700
Data Index: 3598434 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2488. Min Act: -0.1700
Data Index: 4208120 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2488. Min Act: -0.1700
Data Index: 749037 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2331. Min Act: -0.1700
Data Index: 2431695 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2174. Min Act: -0.1700
Data Index: 5293528 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19