Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3948 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.9174. Min Act: -0.1700
Data Index: 5494248 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.8221. Min Act: -0.1700
Data Index: 817962 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.7903. Min Act: -0.1700
Data Index: 498175 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.6624. Min Act: -0.1700
Data Index: 847614 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.5336. Min Act: -0.1698
Data Index: 3969823 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.4851. Min Act: -0.1700
Data Index: 1579359 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.4526. Min Act: -0.1700
Data Index: 7567099 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.4201. Min Act: -0.1700
Data Index: 8725999 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3874. Min Act: -0.1700
Data Index: 6870944 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3711. Min Act: -0.1700
Data Index: 5478432 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3711. Min Act: -0.1700
Data Index: 1131561 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3547. Min Act: -0.1700
Data Index: 8387181 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3711. Min Act: -0.1700
Data Index: 4242743 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3547. Min Act: -0.1699
Data Index: 6189102 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3547. Min Act: -0.1700
Data Index: 6870945 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3383. Min Act: -0.1700
Data Index: 1131559 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3383. Min Act: -0.1700
Data Index: 5983169 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3219. Min Act: -0.1700
Data Index: 5494249 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3219. Min Act: -0.1700
Data Index: 498176 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9174. Min Range: -2.9174
Max Act: 2.3219. Min Act: -0.1700
Data Index: 5478430 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19