Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4313 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3940. Min Range: -7.3940
Max Act: 7.3940. Min Act: -0.1700
Data Index: 3071678 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.8628. Min Act: -0.1700
Data Index: 1012189 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.8003. Min Act: -0.1700
Data Index: 1695192 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.6440. Min Act: -0.1700
Data Index: 6373873 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.6128. Min Act: -0.1700
Data Index: 7095249 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.5503. Min Act: -0.1700
Data Index: 2898384 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.5190. Min Act: -0.1700
Data Index: 8016525 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.5190. Min Act: -0.1700
Data Index: 6216447 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.5190. Min Act: -0.1700
Data Index: 8806240 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.5190. Min Act: -0.1700
Data Index: 6450286 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4878. Min Act: -0.1700
Data Index: 7231702 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4253. Min Act: -0.1700
Data Index: 7635939 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4253. Min Act: -0.1700
Data Index: 2305570 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4253. Min Act: -0.1700
Data Index: 2320327 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4253. Min Act: -0.1700
Data Index: 5021632 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4565. Min Act: -0.1700
Data Index: 5673617 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.3940. Min Act: -0.1700
Data Index: 1341850 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.4253. Min Act: -0.1700
Data Index: 1629438 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.3940. Min Act: -0.1700
Data Index: 3813269 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3940. Min Range: -7.3940
Max Act: 6.3940. Min Act: -0.1700
Data Index: 5032425 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19