Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.3007. Min Act: -0.1700
Data Index: 958689 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.2694. Min Act: -0.1700
Data Index: 8819681 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.2069. Min Act: -0.1700
Data Index: 8534610 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.1444. Min Act: -0.1700
Data Index: 8123421 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.0507. Min Act: -0.1700
Data Index: 8778105 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3007. Min Range: -7.3007
Max Act: 7.0194. Min Act: -0.1700
Data Index: 2968983 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8944. Min Act: -0.1700
Data Index: 5735208 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.9569. Min Act: -0.1700
Data Index: 5682486 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.9257. Min Act: -0.1700
Data Index: 4256933 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8632. Min Act: -0.1700
Data Index: 3293135 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8632. Min Act: -0.1700
Data Index: 997147 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8319. Min Act: -0.1700
Data Index: 7843048 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8007. Min Act: -0.1700
Data Index: 6843054 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8007. Min Act: -0.1700
Data Index: 4131028 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.8007. Min Act: -0.1700
Data Index: 4304620 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.7694. Min Act: -0.1700
Data Index: 2954212 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.7694. Min Act: -0.1700
Data Index: 4237574 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.7694. Min Act: -0.1700
Data Index: 5472559 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.7694. Min Act: -0.1700
Data Index: 651184 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3007. Min Range: -7.3007
Max Act: 6.7382. Min Act: -0.1700
Data Index: 143864 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19