Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.7895. Min Act: -0.1700
Data Index: 4481173 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.7895. Min Act: -0.1700
Data Index: 4294245 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.6958. Min Act: -0.1700
Data Index: 767068 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.6020. Min Act: -0.1700
Data Index: 5891406 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.5083. Min Act: -0.1700
Data Index: 2465191 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.5083. Min Act: -0.1700
Data Index: 1856165 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.4458. Min Act: -0.1700
Data Index: 1892409 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3862435 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3833. Min Act: -0.1700
Data Index: 1003098 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3833. Min Act: -0.1700
Data Index: 171487 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3520. Min Act: -0.1700
Data Index: 5973176 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3520. Min Act: -0.1700
Data Index: 3112806 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3520. Min Act: -0.1700
Data Index: 7319943 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7505924 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3520. Min Act: -0.1700
Data Index: 3158939 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3208. Min Act: -0.1700
Data Index: 379526 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7791797 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.3208. Min Act: -0.1700
Data Index: 8707513 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.2895. Min Act: -0.1700
Data Index: 4154077 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7895. Min Range: -5.7895
Max Act: 5.2895. Min Act: -0.1700
Data Index: 8027485 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19