Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.7916. Min Act: -0.1700
Data Index: 8664046 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.6666. Min Act: -0.1700
Data Index: 1145399 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3853. Min Act: -0.1700
Data Index: 4361030 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3228. Min Act: -0.1700
Data Index: 1295765 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.2916. Min Act: -0.1700
Data Index: 1563974 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.2291. Min Act: -0.1700
Data Index: 3276764 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1978. Min Act: -0.1700
Data Index: 5566162 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1978. Min Act: -0.1700
Data Index: 1856142 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7271652 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1978. Min Act: -0.1700
Data Index: 3120514 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1666. Min Act: -0.1700
Data Index: 4929228 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7213420 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1353. Min Act: -0.1700
Data Index: 6386370 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3078842 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1041. Min Act: -0.1700
Data Index: 7807470 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1041. Min Act: -0.1700
Data Index: 1302693 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.1041. Min Act: -0.1700
Data Index: 1519642 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4524186 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.0728. Min Act: -0.1700
Data Index: 8550035 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.0728. Min Act: -0.1700
Data Index: 1856137 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19