Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0145. Min Range: -5.0145
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2999316 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 7485540 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7958. Min Act: -0.1700
Data Index: 5821938 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7645. Min Act: -0.1700
Data Index: 541245 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7333. Min Act: -0.1700
Data Index: 4130226 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7333. Min Act: -0.1700
Data Index: 6129219 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7645. Min Act: -0.1700
Data Index: 5199095 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6708. Min Act: -0.1700
Data Index: 4765426 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.7020. Min Act: -0.1700
Data Index: 6602397 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6708. Min Act: -0.1700
Data Index: 6249215 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6708. Min Act: -0.1700
Data Index: 3576230 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6395. Min Act: -0.1700
Data Index: 6209867 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6083. Min Act: -0.1700
Data Index: 5285362 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.6083. Min Act: -0.1700
Data Index: 1345274 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5770. Min Act: -0.1700
Data Index: 7684661 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4361236 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5458. Min Act: -0.1700
Data Index: 8175402 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5770. Min Act: -0.1700
Data Index: 6428272 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5770. Min Act: -0.1700
Data Index: 6677346 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.5458. Min Act: -0.1700
Data Index: 4657595 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19