Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3774. Min Act: -0.1700
Data Index: 3377366 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3862. Min Act: -0.1700
Data Index: 2928518 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3686. Min Act: -0.1700
Data Index: 7542591 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3686. Min Act: -0.1700
Data Index: 3301499 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3598. Min Act: -0.1700
Data Index: 1373859 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3510. Min Act: -0.1700
Data Index: 3790855 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3422. Min Act: -0.1700
Data Index: 797425 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3510. Min Act: -0.1700
Data Index: 3251642 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3333. Min Act: -0.1700
Data Index: 1857432 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3422. Min Act: -0.1700
Data Index: 4558018 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3333. Min Act: -0.1700
Data Index: 3542550 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3422. Min Act: -0.1690
Data Index: 2586339 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3333. Min Act: -0.1700
Data Index: 4505907 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3422. Min Act: -0.1687
Data Index: 206849 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3245. Min Act: -0.1700
Data Index: 7839519 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3245. Min Act: -0.1700
Data Index: 4642840 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3245. Min Act: -0.1700
Data Index: 7894372 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3157. Min Act: -0.1700
Data Index: 7393837 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3157. Min Act: -0.1700
Data Index: 5870305 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3862. Min Range: -1.3862
Max Act: 1.3157. Min Act: -0.1699
Data Index: 6738945 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19