Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1366. Min Range: -8.1366
Max Act: 8.1366. Min Act: -0.1700
Data Index: 1151812 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1366. Min Range: -8.1366
Max Act: 8.0116. Min Act: -0.1700
Data Index: 2774617 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.7304. Min Act: -0.1700
Data Index: 79845 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.7304. Min Act: -0.1700
Data Index: 1477672 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.6366. Min Act: -0.1700
Data Index: 6500025 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.5116. Min Act: -0.1700
Data Index: 7034954 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.4491. Min Act: -0.1700
Data Index: 2186893 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.4491. Min Act: -0.1700
Data Index: 8473958 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.4491. Min Act: -0.1700
Data Index: 2420042 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.4491. Min Act: -0.1700
Data Index: 3156683 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.4491. Min Act: -0.1700
Data Index: 5923087 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.3554. Min Act: -0.1700
Data Index: 8496073 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.3241. Min Act: -0.1700
Data Index: 5550424 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.3241. Min Act: -0.1700
Data Index: 5770940 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2929. Min Act: -0.1700
Data Index: 6958909 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2616. Min Act: -0.1700
Data Index: 6967444 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2616. Min Act: -0.1700
Data Index: 6491054 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2929. Min Act: -0.1700
Data Index: 6249216 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2304. Min Act: -0.1700
Data Index: 3072986 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1366. Min Range: -8.1366
Max Act: 7.2304. Min Act: -0.1700
Data Index: 8584524 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19