Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.3268. Min Act: -0.1700
Data Index: 6696262 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.2643. Min Act: -0.1700
Data Index: 7373217 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.1081. Min Act: -0.1700
Data Index: 1460450 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7514597 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 6475793 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0456. Min Act: -0.1700
Data Index: 5849174 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7961609 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 2503814 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 5141807 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9518. Min Act: -0.1700
Data Index: 4782421 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9206. Min Act: -0.1700
Data Index: 4300489 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9206. Min Act: -0.1700
Data Index: 2060887 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9206. Min Act: -0.1700
Data Index: 2083541 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8581. Min Act: -0.1700
Data Index: 3506774 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8268. Min Act: -0.1700
Data Index: 3579252 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8581. Min Act: -0.1700
Data Index: 4998147 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8268. Min Act: -0.1700
Data Index: 1089260 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.7956. Min Act: -0.1700
Data Index: 3264401 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.7331. Min Act: -0.1700
Data Index: 2371869 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8581. Min Act: -0.1700
Data Index: 965715 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19